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

    Neuronpedia

    INDEX
    Explanations

    filter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .square
    -0.07
    xab
    -0.07
     uname
    -0.06
     cosine
    -0.06
     mak
    -0.06
    数量
    -0.06
    ProcAddress
    -0.06
    (loc
    -0.06
     nas
    -0.06
    cad
    -0.06
    POSITIVE LOGITS
     Filter
    0.10
    Filter
    0.10
     filters
    0.10
     filter
    0.09
    filter
    0.09
    검
    0.08
    filters
    0.08
     filtered
    0.08
     검
    0.08
     filtro
    0.08
    Act Density 0.021%

    No Known Activations