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

    Neuronpedia

    INDEX
    Explanations

    scroll

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cst
    -0.06
     waiter
    -0.06
     जम
    -0.06
    _rl
    -0.06
     पश
    -0.06
     十
    -0.06
     приход
    -0.06
    ﾐ
    -0.06
     surtout
    -0.06
    progressbar
    -0.06
    POSITIVE LOGITS
    ans
    0.07
     назва
    0.07
    Ent
    0.07
     الدر
    0.07
     scans
    0.06
     Expenses
    0.06
     Adoption
    0.06
    .labels
    0.06
     Pear
    0.06
    532
    0.06
    Act Density 0.000%

    No Known Activations