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

    Neuronpedia

    INDEX
    Explanations

    examples and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.65
    en
    0.56
    ن
    0.55
    au
    0.52
    ने
    0.52
     ouders
    0.52
    ;
    0.52
    oo
    0.51
     numerosi
    0.50
    您
    0.50
    POSITIVE LOGITS
     propel
    0.50
     यादव
    0.50
    <unused686>
    0.49
     ምክንያት
    0.48
     యుద్ధ
    0.46
    geoType
    0.46
     collide
    0.46
    ImageBeforeText
    0.46
     bầu
    0.45
     яй
    0.44
    Act Density 0.000%

    No Known Activations