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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Apply
    -0.08
    镶
    -0.07
    早点
    -0.07
    Виде
    -0.07
    Picker
    -0.07
     Exact
    -0.07
    rès
    -0.07
    (Graphics
    -0.07
    ựa
    -0.07
     Seq
    -0.07
    POSITIVE LOGITS
    袋
    0.07
    держива
    0.07
    .startswith
    0.06
     malt
    0.06
    ListGroup
    0.06
    ','
    0.06
     lider
    0.06
    AFE
    0.06
    챃
    0.06
    ort
    0.06
    Act Density 0.000%

    No Known Activations