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

    Neuronpedia

    INDEX
    Explanations

    Unstructured text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Algebra
    -0.07
    pher
    -0.06
    andWhere
    -0.06
    ridden
    -0.06
     wis
    -0.06
    跑
    -0.06
    σματα
    -0.06
    grey
    -0.06
     unlawful
    -0.06
    웃
    -0.06
    POSITIVE LOGITS
    Constructed
    0.07
    führ
    0.07
    iedo
    0.06
    ピ
    0.06
     �
    0.06
     jednotlivých
    0.06
     lodash
    0.06
    нося
    0.06
     дев
    0.06
    :x
    0.06
    Act Density 0.257%

    No Known Activations