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

    Neuronpedia

    INDEX
    Explanations

    alternate between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    1.19
     at
    1.05
     in
    1.05
     al
    1.02
    0
    1.01
     on
    1.00
     are
    0.98
    "
    0.96
     kes
    0.93
     در
    0.92
    POSITIVE LOGITS
    ಥವಾ
    0.87
     Altern
    0.86
    터
    0.86
    зыва
    0.82
    ገልግሎ
    0.82
    스로
    0.79
    스를
    0.77
    Altern
    0.77
    方法
    0.76
    ク
    0.75
    Act Density 0.010%

    No Known Activations