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

    Neuronpedia

    INDEX
    Explanations

    center

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _study
    -0.07
     PURE
    -0.07
     discrete
    -0.07
    .read
    -0.07
    .input
    -0.06
    .allocate
    -0.06
    ftype
    -0.06
    Boot
    -0.06
    -summary
    -0.06
    _old
    -0.06
    POSITIVE LOGITS
    입
    0.06
     ang
    0.06
    沖
    0.06
    àng
    0.06
     indonesia
    0.06
    แสดง
    0.06
    ────
    0.06
    만남
    0.06
     peč
    0.06
    NU
    0.06
    Act Density 0.006%

    No Known Activations