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

    Neuronpedia

    INDEX
    Explanations

    list of variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    加えて
    0.74
    examtype
    0.73
    ف
    0.73
    ش
    0.71
    volvement
    0.69
    americanos
    0.67
     currentDate
    0.67
    ဠ
    0.66
    ӵ
    0.66
    studentid
    0.65
    POSITIVE LOGITS
    T
    1.05
    R
    1.02
    P
    0.98
    L
    0.98
    M
    0.96
    N
    0.94
    C
    0.91
    S
    0.89
    B
    0.89
     don
    0.86
    Act Density 0.000%

    No Known Activations