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

    Neuronpedia

    INDEX
    Explanations

    lines/equals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    果然
    -0.07
    司
    -0.07
     solver
    -0.07
     matrix
    -0.07
     gradient
    -0.07
    ảng
    -0.06
     Alam
    -0.06
     landscape
    -0.06
     Mu
    -0.06
    Sc
    -0.06
    POSITIVE LOGITS
    摊
    0.07
    few
    0.07
    /windows
    0.07
     cauliflower
    0.07
    thew
    0.07
    .black
    0.07
     ----------------
    0.07
     featured
    0.07
    _COMPLEX
    0.07
    接受采访
    0.07
    Act Density 0.001%

    No Known Activations