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

    Neuronpedia

    INDEX
    Explanations

    symbols and specific formatting characters often used in programming or mathematical equations

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

    Tokens after questions, mixed with various categories labels

    np_acts-logits-general · gemini-2.0-flash

    specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OFDb
    -0.53
    -
    -0.52
     们
    -0.52
    jspx
    -0.49
     round
    -0.48
    hdessä
    -0.47
     as
    -0.47
     man
    -0.47
     son
    -0.46
    FormTagHelper
    -0.46
    POSITIVE LOGITS
    thâu
    0.74
     Infórmanos
    0.68
     nahilalakip
    0.66
    riwal
    0.64
     Ptole
    0.64
    ciating
    0.63
    VersionUID
    0.63
    ImageContext
    0.63
     calendriers
    0.62
     Hyperion
    0.61
    Act Density 0.867%

    No Known Activations