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

    Neuronpedia

    INDEX
    Explanations

    applicable law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Crimea
    0.46
    લ્ડ
    0.43
     ={
    0.42
     DMBT
    0.42
     Rubén
    0.42
    гиз
    0.41
     medicamentos
    0.40
     Agustín
    0.40
     Luís
    0.40
     Pall
    0.39
    POSITIVE LOGITS
    However
    0.45
    و
    0.44
    鐘
    0.43
     grader
    0.43
    forcing
    0.41
     However
    0.41
    ረጥ
    0.40
     forcing
    0.40
     nyata
    0.40
    Similarly
    0.38
    Act Density 0.000%

    No Known Activations