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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific data attributes

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

    UUIDs starting with "f136e223-a"

    np_acts-logits-general · gemini-2.0-flash

    GUIDs and hex strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    -0.71
    u
    -0.65
    i
    -0.62
    c
    -0.58
    an
    -0.58
    ں
    -0.57
    ti
    -0.55
    aS
    -0.54
    UnusedPrivate
    -0.53
    te
    -0.53
    POSITIVE LOGITS
    ValueStyle
    0.58
    angliski
    0.55
     متعلقه
    0.55
     كومونز
    0.54
     kasarigan
    0.54
     InputDecoration
    0.53
    enumii
    0.50
     Réponses
    0.48
    脚注の使い方
    0.48
    enumi
    0.47
    Act Density 0.175%

    No Known Activations