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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acements
    -0.07
    prec
    -0.07
    .Camera
    -0.06
    tones
    -0.06
    тро
    -0.06
    оба
    -0.06
    psc
    -0.06
    웠
    -0.06
    Faces
    -0.06
    mb
    -0.06
    POSITIVE LOGITS
    Dyn
    0.07
     Monsanto
    0.06
     Enumerator
    0.06
     "))↵
    0.06
     hypo
    0.06
     кот
    0.06
     oč
    0.06
     aunt
    0.06
     lease
    0.06
    VertexUvs
    0.06
    Act Density 0.000%

    No Known Activations