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

    Neuronpedia

    INDEX
    Explanations

    ">"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    市级
    -0.07
    .type
    -0.07
    mathrm
    -0.07
    㺄
    -0.07
     программ
    -0.07
    FRAME
    -0.07
    (part
    -0.07
    approximately
    -0.07
    #[
    -0.06
    _type
    -0.06
    POSITIVE LOGITS
    淦
    0.08
    房价
    0.08
    :request
    0.07
    親
    0.07
    .Italic
    0.07
     regulate
    0.07
     Miguel
    0.07
    곽
    0.07
    丢了
    0.07
    优越
    0.07
    Act Density 0.017%

    No Known Activations