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

    Neuronpedia

    INDEX
    Explanations

    thin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thin
    -0.89
     minor
    -0.88
    minor
    -0.85
    Minor
    -0.77
     Minor
    -0.72
    MINOR
    -0.67
     MINOR
    -0.65
     minori
    -0.65
    UnusedPrivate
    -0.64
    Referanser
    -0.64
    POSITIVE LOGITS
     breasted
    0.50
    breasted
    0.50
    campal
    0.49
     przewod
    0.46
    assable
    0.46
    losigkeit
    0.44
    ัตว์
    0.44
    гії
    0.43
     Побе
    0.42
     Huns
    0.42
    Act Density 0.198%

    No Known Activations