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

    Neuronpedia

    INDEX
    Explanations

    -basic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Asia
    -0.07
     jj
    -0.07
    .transparent
    -0.07
    USH
    -0.06
    FXML
    -0.06
    سئ
    -0.06
    /events
    -0.06
    .drawString
    -0.06
     Fab
    -0.06
    商品
    -0.06
    POSITIVE LOGITS
     język
    0.07
    clf
    0.07
    ippo
    0.07
    _months
    0.06
    _details
    0.06
    eldon
    0.06
    ’↵↵
    0.06
    平
    0.06
     Jerome
    0.06
    ta
    0.06
    Act Density 0.001%

    No Known Activations