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

    Neuronpedia

    INDEX
    Explanations

    avant-garde

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     keer
    0.81
     Wagen
    0.80
    vek
    0.79
    𝑛
    0.78
     ścian
    0.76
    boost
    0.74
     Reb
    0.72
     ガー
    0.72
     taxas
    0.71
     Happens
    0.71
    POSITIVE LOGITS
     survival
    0.78
     linkedin
    0.68
    fromUtf
    0.68
    ോള
    0.67
    प्रथम
    0.67
     first
    0.67
     investigative
    0.66
    assment
    0.66
     quar
    0.65
    ึ้น
    0.65
    Act Density 0.001%

    No Known Activations