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

    Neuronpedia

    INDEX
    Explanations

    ..

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;?>
    -0.06
    .point
    -0.06
    ヽ
    -0.06
     relat
    -0.06
     supermarkets
    -0.06
    าต
    -0.06
    國
    -0.06
    _photos
    -0.06
    Marcus
    -0.06
     和
    -0.06
    POSITIVE LOGITS
     Instances
    0.07
    ControlItem
    0.07
     li
    0.07
    .isDebugEnabled
    0.07
     Automatically
    0.06
     hh
    0.06
     hopping
    0.06
    療
    0.06
     nær
    0.06
    -compose
    0.06
    Act Density 0.000%

    No Known Activations