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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and prohibitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.50
     for
    0.35
    コンピュータ
    0.35
    rett
    0.34
    glColor
    0.33
     rescaling
    0.33
    あります
    0.33
     फॉर
    0.33
    monia
    0.32
    í
    0.32
    POSITIVE LOGITS
    ی
    0.49
    на
    0.49
    ق
    0.46
     has
    0.44
     is
    0.41
     Etappe
    0.41
     would
    0.38
    dır
    0.38
     {\
    0.38
     will
    0.38
    Act Density 0.013%

    No Known Activations