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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ticket
    -0.08
     remark
    -0.07
    Pix
    -0.06
    �
    -0.06
    Lik
    -0.06
    Пол
    -0.06
     vivid
    -0.06
    Bird
    -0.06
    OO
    -0.06
     czy
    -0.06
    POSITIVE LOGITS
     ruin
    0.06
    ンプ
    0.06
    operative
    0.06
    선거
    0.06
     mp
    0.06
    nych
    0.06
    unct
    0.06
     fracking
    0.06
    aryl
    0.06
    �t
    0.06
    Act Density 0.000%

    No Known Activations