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

    Neuronpedia

    INDEX
    Explanations

    knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vrouwen
    -0.07
    ickt
    -0.07
    年輕
    -0.07
    ϊ
    -0.07
    _Rel
    -0.07
     helmet
    -0.07
     mannen
    -0.07
    EMY
    -0.07
    ʟ
    -0.07
    🦸
    -0.07
    POSITIVE LOGITS
    Vector
    0.07
    村
    0.07
     dispatch
    0.07
     biochemical
    0.07
     substitution
    0.07
     possessed
    0.07
     White
    0.07
    ":
↵
    0.06
    ясь
    0.06
     deco
    0.06
    Act Density 0.006%

    No Known Activations