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

    Neuronpedia

    INDEX
    Explanations

    proactive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     większo
    -0.08
    .jet
    -0.07
    aves
    -0.07
     leggings
    -0.07
     kenn
    -0.07
    鞠
    -0.07
    呼
    -0.07
    _CSS
    -0.07
     cuz
    -0.07
     registro
    -0.07
    POSITIVE LOGITS
     neutrality
    0.07
    +"/
    0.06
    🌝
    0.06
     המ
    0.06
    tón
    0.06
    tica
    0.06
    MC
    0.06
    (`/
    0.06
     leurs
    0.06
    +l
    0.06
    Act Density 0.003%

    No Known Activations