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

    Neuronpedia

    INDEX
    Explanations

    color definitions in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ministers
    0.37
    მას
    0.37
     naturales
    0.36
     Wedgwood
    0.35
     Sted
    0.35
     Geografia
    0.34
     poop
    0.34
     jasper
    0.34
    ষ্টি
    0.33
     Ос
    0.33
    POSITIVE LOGITS
    umma
    0.37
    snake
    0.36
    лизова
    0.35
    annotate
    0.35
     பாம்பு
    0.34
    校园
    0.34
    rench
    0.33
    rava
    0.32
    azza
    0.32
     በሽታ
    0.32
    Act Density 0.007%

    No Known Activations