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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    গ
    -0.90
     warned
    -0.83
     those
    -0.81
     noel
    -0.77
     calculating
    -0.77
     cera
    -0.75
    tisgarh
    -0.75
    lą
    -0.75
     Mahesh
    -0.74
    ään
    -0.71
    POSITIVE LOGITS
     +
    0.90
     "+
    0.86
    >>(
    0.82
     :(
    0.82
     $(
    0.81
     Tel
    0.80
    Tel
    0.79
    8
    0.78
    이다
    0.76
     }(
    0.76
    Act Density 0.035%

    No Known Activations