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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue or reported speech

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

    Preceding a pronoun (he/him/his)

    np_acts-logits-general · gemini-2.0-flash

    he, him, his pronoun usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.95
    tagHelperRunner
    -0.92
     initComponents
    -0.91
     Efq
    -0.88
    endphp
    -0.87
    +#+#
    -0.84
     ویکی‌پدیای
    -0.83
    RenderAtEndOf
    -0.83
     ſeveral
    -0.83
    AnchorStyles
    -0.82
    POSITIVE LOGITS
     Mr
    0.57
     him
    0.57
     通販
    0.53
    (
    0.50
     he
    0.49
    はじめに
    0.48
    Mr
    0.47
    *
    0.44
     او
    0.43
    ^
    0.42
    Act Density 0.631%

    No Known Activations