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

    Neuronpedia

    INDEX
    Explanations

    times after at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uz
    0.73
     Produto
    0.73
     horas
    0.71
    Produto
    0.71
    ൂര്‍
    0.71
    urion
    0.69
    producto
    0.69
     hours
    0.68
    レース
    0.68
     सेल्स
    0.67
    POSITIVE LOGITS
     Noon
    1.00
     noon
    1.00
     midnight
    0.83
     साढ़े
    0.80
     ৭
    0.80
    noon
    0.72
     doubts
    0.72
     doubted
    0.69
    ８
    0.69
     Doubt
    0.68
    Act Density 0.054%

    No Known Activations