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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RENDER
    -0.07
    clar
    -0.06
    厅
    -0.06
     Liu
    -0.06
     计
    -0.06
    azine
    -0.06
    Fac
    -0.06
    盖
    -0.06
     hấp
    -0.06
     sanitary
    -0.06
    POSITIVE LOGITS
    .review
    0.08
    -css
    0.07
    bitcoin
    0.07
    natal
    0.06
     Při
    0.06
    ->$
    0.06
    mess
    0.06
    mo
    0.06
    .hs
    0.06
    ayaran
    0.06
    Act Density 0.028%

    No Known Activations