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

    Neuronpedia

    INDEX
    Explanations

    conditional statements in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.84
    {}{
    0.73
    $(\
    0.73
     No
    0.72
     Alive
    0.71
     no
    0.70
     ($\
    0.69
     Recorded
    0.67
    0.67
     Good
    0.67
    POSITIVE LOGITS
    并不
    0.84
    为
    0.82
     فهر
    0.82
    约为
    0.81
     স্পর্শ
    0.80
    十五
    0.80
    ۱۲
    0.79
    间隔
    0.79
     égard
    0.79
    riss
    0.79
    Act Density 0.044%

    No Known Activations