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

    Neuronpedia

    INDEX
    Explanations

    emotional states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ium
    0.29
    ires
    0.28
    lem
    0.25
     are
    0.25
    ations
    0.24
    s
    0.24
    ugg
    0.24
    ios
    0.24
     It
    0.23
    uje
    0.23
    POSITIVE LOGITS
    ু
    0.32
    ר
    0.30
     Alek
    0.29
    ي
    0.29
     Olimpi
    0.29
     Aralık
    0.28
     һәм
    0.28
     especial
    0.27
    il
    0.27
    ad
    0.27
    Act Density 1.166%

    No Known Activations