Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting elements in coding or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Characters surrounding text formatting symbols

    np_acts-logits-general · gemini-2.0-flash

    special characters and foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createState
    -0.84
    HasAnnotation
    -0.81
    tonsoft
    -0.70
    Hochspringen
    -0.70
     Himo
    -0.70
     BorderRadius
    -0.69
    usermodel
    -0.62
     AspNetCore
    -0.61
    ElementException
    -0.60
    UnusedPrivate
    -0.60
    POSITIVE LOGITS
    بالإنجليزية
    0.78
     zvuky
    0.64
     متعلقه
    0.59
     Quelles
    0.57
     suprême
    0.56
    llbracket
    0.55
     grammi
    0.55
    떻
    0.54
     obligé
    0.54
     émer
    0.51
    Act Density 1.196%

    No Known Activations