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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words containing "self" or "co" to indicate some kind of interaction or relationship

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -
    -1.28
    (
    -0.82
    /
    -0.74
    .
    -0.64
    :
    -0.61
    \
    -0.60
    '
    -0.60
    _
    -0.57
    ,
    -0.56
    =
    -0.55
    POSITIVE LOGITS
     itſelf
    1.24
     myſelf
    0.94
    ſelf
    0.93
    StoryboardSegue
    0.93
    ſelves
    0.92
     ་་
    0.92
     pleaſure
    0.90
     raiſ
    0.90
    ']))
    0.86
     Anſ
    0.85
    Act Density 2.178%

    No Known Activations