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

    Neuronpedia

    INDEX
    Explanations

    prioritizing decisions and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.66
    usions
    0.49
    ta
    0.49
    shire
    0.48
    astics
    0.48
    vi
    0.47
    umping
    0.47
    spar
    0.46
     ഏത
    0.46
    j
    0.46
    POSITIVE LOGITS
    ி
    0.69
    ي
    0.68
    ای
    0.63
     localização
    0.62
    ন
    0.61
    ่
    0.59
    ر
    0.58
    노
    0.58
    مو
    0.57
    માં
    0.56
    Act Density 0.540%

    No Known Activations