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

    Neuronpedia

    INDEX
    Explanations

    .Assert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obstacle
    -0.07
    I
    -0.06
    plane
    -0.06
    amel
    -0.06
    enti
    -0.06
     metic
    -0.06
     Baghdad
    -0.06
     serão
    -0.06
    ects
    -0.06
    方
    -0.06
    POSITIVE LOGITS
     afirm
    0.07
     Emacs
    0.07
     significant
    0.06
    ITableView
    0.06
     minul
    0.06
    _predicted
    0.06
     [$
    0.06
    (angle
    0.06
     Burg
    0.06
    험
    0.06
    Act Density 0.001%

    No Known Activations