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

    Neuronpedia

    INDEX
    Explanations

    famous person/object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ות
    0.66
    lite
    0.61
    적으로
    0.60
     seemingly
    0.60
    Ḫ
    0.59
    ："
    0.59
     indeterminate
    0.58
    Prediction
    0.57
    ：
    0.57
     construction
    0.57
    POSITIVE LOGITS
     famoso
    0.86
    ㍍
    0.84
     cuja
    0.81
     cujo
    0.80
     нужен
    0.79
     cantante
    0.77
     pintor
    0.77
     bekannte
    0.77
     famosa
    0.77
     dijo
    0.75
    Act Density 0.000%

    No Known Activations