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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Mouse
    -0.07
    .propTypes
    -0.07
    곯
    -0.06
     useRouter
    -0.06
     urb
    -0.06
     Univers
    -0.06
    哕
    -0.06
     relat
    -0.06
    -remove
    -0.06
    viol
    -0.06
    POSITIVE LOGITS
    KV
    0.07
     duty
    0.07
     ROUND
    0.07
     дней
    0.07
    ENCH
    0.07
     ואני
    0.07
    Graphic
    0.07
    _traffic
    0.07
    鲁能
    0.07
    _WHITE
    0.07
    Act Density 0.001%

    No Known Activations