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

    Neuronpedia

    INDEX
    Explanations

    crisis hotline numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uidos
    0.38
     हुआ
    0.37
    льной
    0.37
    mington
    0.37
     maravilh
    0.37
    行业
    0.36
    華
    0.36
     Elektrokh
    0.35
    }($
    0.35
     thermique
    0.35
    POSITIVE LOGITS
    冗
    0.41
    Խ
    0.38
     సెల
    0.37
    iteracy
    0.37
     appointment
    0.36
    ́t
    0.36
     Мо
    0.36
    폭
    0.35
    𝕞
    0.35
     fontstyle
    0.35
    Act Density 0.003%

    No Known Activations