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

    Neuronpedia

    INDEX
    Explanations

    mp.4, .7, .json, mp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stä
    0.96
    s
    0.93
    rt
    0.91
    register
    0.91
    sr
    0.87
    sst
    0.86
    sized
    0.83
    rs
    0.81
    gest
    0.81
    Is
    0.80
    POSITIVE LOGITS
     酸
    0.79
     Từ
    0.75
     充電
    0.71
     温度
    0.69
     onions
    0.68
     écran
    0.68
     kinetics
    0.68
    ونا
    0.67
     mécanisme
    0.67
    ва
    0.66
    Act Density 0.013%

    No Known Activations