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

    Neuronpedia

    INDEX
    Explanations

    tables and code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.72
    不下
    0.65
    il
    0.63
    z
    0.63
    .
    0.61
    éb
    0.61
    1
    0.59
    ك
    0.59
    áte
    0.58
    quisitos
    0.58
    POSITIVE LOGITS
     concierge
    0.60
     Feminist
    0.59
     it
    0.59
    ्यु
    0.58
     caucus
    0.58
     feminist
    0.57
     It
    0.56
     अवधारणा
    0.56
     sash
    0.55
     三菱
    0.55
    Act Density 0.000%

    No Known Activations