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

    Neuronpedia

    INDEX
    Explanations

    removal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pru
    -0.06
     Bent
    -0.06
     lug
    -0.06
     beş
    -0.06
    \s
    -0.06
     bought
    -0.06
    }.
    -0.06
     crib
    -0.06
     fixes
    -0.06
     frat
    -0.06
    POSITIVE LOGITS
     exports
    0.06
    ('\
    0.06
    FXML
    0.06
    xED
    0.06
     Legislation
    0.06
    DV
    0.06
    ラク
    0.06
     Cartoon
    0.06
    _Destroy
    0.06
    DG
    0.06
    Act Density 0.002%

    No Known Activations