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

    Neuronpedia

    INDEX
    Explanations

    divisions, purpose, permission, Alice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ták
    2.27
    ો
    1.98
    十玖章
    1.89
    十肆章
    1.86
    十柒章
    1.84
    十伍章
    1.83
     উহার
    1.81
    玖章
    1.80
    ு
    1.80
    場合に
    1.78
    POSITIVE LOGITS
    .
    1.17
     eventually
    1.10
     quite
    1.09
    …
    1.09
     just
    1.09
    ,
    1.08
    Г
    1.07
     basically
    1.06
     you
    1.04
     people
    1.04
    Act Density 3.022%

    No Known Activations