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

    Neuronpedia

    INDEX
    Explanations

    expressions related to assisting and informing others

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

    followed by prepositions or articles

    np_acts-logits-general · gemini-2.0-flash

    verbs followed by subsequent words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.92
    ”.
    -0.71
    ".
    -0.63
    .”
    -0.62
    ’.
    -0.59
    。
    -0.54
    '.
    -0.53
    ).
    -0.53
     właśnie
    -0.51
    ."
    -0.51
    POSITIVE LOGITS
     kasarigan
    1.13
     كومونز
    1.06
     الرياضيه
    1.06
     Мексичка
    0.98
    )*/
    0.88
    MigrationBuilder
    0.87
     חיצוניים
    0.85
    protoimpl
    0.81
    abetes
    0.81
    __':
    0.81
    Act Density 0.517%

    No Known Activations