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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gage
    -0.07
    ーム
    -0.07
    くれた
    -0.07
     Heating
    -0.06
     我
    -0.06
    tour
    -0.06
    óst
    -0.06
     raison
    -0.06
    رخ
    -0.06
    Adult
    -0.06
    POSITIVE LOGITS
    权限
    0.07
     conclus
    0.07
    $ret
    0.07
     هل
    0.06
    渡
    0.06
    Modifier
    0.06
     '-
    0.06
     yaklaşık
    0.06
    @js
    0.06
     Nurs
    0.06
    Act Density 0.175%

    No Known Activations