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

    Neuronpedia

    INDEX
    Explanations

    disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hecho
    0.48
     يتح
    0.45
     fatto
    0.45
     sich
    0.44
    阎
    0.43
     kế
    0.42
     Takes
    0.42
     takes
    0.42
     promotes
    0.42
     slightest
    0.41
    POSITIVE LOGITS
    DIS
    0.62
     DIS
    0.52
    dis
    0.52
    clamation
    0.47
    claim
    0.47
    Dis
    0.46
     дис
    0.46
    nlp
    0.45
    diss
    0.44
    maxLength
    0.43
    Act Density 0.045%

    No Known Activations