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

    Neuronpedia

    INDEX
    Explanations

    say something racist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dependencies
    0.52
    sr
    0.50
     :/
    0.50
    ->_
    0.49
    ทยาลัย
    0.49
    cf
    0.48
    কে
    0.47
    cion
    0.47
    t
    0.46
     এ
    0.46
    POSITIVE LOGITS
    Processed
    0.45
    ազմ
    0.44
    itical
    0.44
    STS
    0.43
    ösen
    0.42
     loa
    0.42
    组织的
    0.41
    يط
    0.40
     financiar
    0.40
    組織
    0.39
    Act Density 0.000%

    No Known Activations