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

    Neuronpedia

    INDEX
    Explanations

    roid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [first
    -0.06
     Lazy
    -0.06
     kdy
    -0.06
     만들어
    -0.06
     Drops
    -0.06
    _s
    -0.06
    .’
    -0.06
    _Is
    -0.06
    Æ
    -0.06
    _cores
    -0.06
    POSITIVE LOGITS
    Israel
    0.07
    professional
    0.07
    шибка
    0.07
     accounted
    0.06
    modelName
    0.06
     minorities
    0.06
    vements
    0.06
    -confidence
    0.06
    nergie
    0.06
    However
    0.06
    Act Density 0.000%

    No Known Activations