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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tabla
    -0.07
    ४
    -0.06
    495
    -0.06
    vented
    -0.06
    -document
    -0.06
    ูร
    -0.06
    .dao
    -0.06
    ceiver
    -0.06
    вад
    -0.06
    cono
    -0.06
    POSITIVE LOGITS
    **,
    0.07
    nj
    0.07
    /Q
    0.07
    ンの
    0.06
    *s
    0.06
    }(
    0.06
    \R
    0.06
     dj
    0.06
    VERTEX
    0.06
    ».↵↵
    0.06
    Act Density 0.009%

    No Known Activations