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

    Neuronpedia

    INDEX
    Explanations

    error occurred

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     survives
    1.60
     becomes
    1.56
     disappears
    1.48
     attracts
    1.43
     goes
    1.42
     gets
    1.41
     gives
    1.35
     begins
    1.35
     loses
    1.34
     succeeds
    1.33
    POSITIVE LOGITS
     reflexion
    0.91
     മെ
    0.81
    מל
    0.80
    Наша
    0.79
    zub
    0.78
    calaureate
    0.77
     bárm
    0.77
     سط
    0.77
    upan
    0.77
    Owned
    0.76
    Act Density 0.020%

    No Known Activations