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
    'ı
    -0.06
     efect
    -0.06
    ským
    -0.06
     toàn
    -0.06
    +len
    -0.06
     firefighters
    -0.06
     organis
    -0.06
    /team
    -0.06
    aw
    -0.06
    z
    -0.06
    POSITIVE LOGITS
    usband
    0.07
    ProducesResponseType
    0.07
     getMax
    0.06
    ünde
    0.06
    grounds
    0.06
    .getOwnProperty
    0.06
     IG
    0.06
     discomfort
    0.06
    鱼
    0.06
     suspicions
    0.06
    Act Density 0.007%

    No Known Activations