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

    Neuronpedia

    INDEX
    Explanations

    input or queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.79
     survival
    0.69
     extermin
    0.68
    Stats
    0.68
    1
    0.68
     Ab
    0.68
     cron
    0.66
     lifes
    0.65
    J
    0.64
    Ce
    0.64
    POSITIVE LOGITS
     inputs
    1.72
     Inputs
    1.68
     输入
    1.68
     input
    1.63
     Input
    1.59
    Inputs
    1.56
    入力
    1.54
    输入
    1.54
    输入的
    1.53
    input
    1.53
    Act Density 6.684%

    No Known Activations