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

    Neuronpedia

    INDEX
    Explanations

    vector dot products

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     заранее
    -0.09
     шара
    -0.08
     велосип
    -0.08
    _BOOT
    -0.08
     навер
    -0.08
     lithium
    -0.08
     startup
    -0.08
    ORITY
    -0.07
    ICEF
    -0.07
    BOOT
    -0.07
    POSITIVE LOGITS
     scalar
    0.10
     Scalar
    0.10
    交流
    0.09
     tensors
    0.09
    _scalar
    0.09
    producto
    0.09
     Bras
    0.09
    .scalar
    0.08
    scalar
    0.08
     fragen
    0.08
    Act Density 0.023%

    No Known Activations