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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dope
    -0.08
    (where
    -0.07
     compound
    -0.06
    rogram
    -0.06
    <n
    -0.06
     staying
    -0.06
    =x
    -0.06
     Movie
    -0.06
     Bash
    -0.06
    うち
    -0.06
    POSITIVE LOGITS
     Thema
    0.07
     unsubscribe
    0.07
     matrimon
    0.06
    .tpl
    0.06
    �试
    0.06
     Predictor
    0.06
    .Ass
    0.06
    .Th
    0.06
    castle
    0.06
     rencontrer
    0.06
    Act Density 0.011%

    No Known Activations