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

    Neuronpedia

    INDEX
    Explanations

    calculate, article, CPU, Market

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CLIENTI
    0.46
     అమ్మ
    0.43
     요구
    0.42
    featuresMatrix
    0.41
     sexu
    0.41
    वाइन
    0.40
    섹
    0.40
    女
    0.40
    Loan
    0.40
     jaanu
    0.40
    POSITIVE LOGITS
     Turing
    0.48
    <h2>
    0.40
    ک
    0.40
    DESCRIPTION
    0.39
    pesar
    0.39
    uff
    0.39
     ultraviolet
    0.38
     actual
    0.38
    具体的
    0.38
    length
    0.38
    Act Density 0.000%

    No Known Activations