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

    Neuronpedia

    INDEX
    Explanations

    knot of emotion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Abstracts
    0.75
    ना
    0.71
    ть
    0.70
     accessoires
    0.69
     Axes
    0.68
     were
    0.66
     escal
    0.65
     étapes
    0.65
     avantages
    0.65
    ce
    0.64
    POSITIVE LOGITS
    ﺎ
    0.85
    dincer
    0.79
    ᄑ
    0.77
    İM
    0.76
    ОВ
    0.75
    𝓭
    0.74
    ів
    0.73
    हत्या
    0.73
    kswagen
    0.73
    энд
    0.73
    Act Density 0.001%

    No Known Activations