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

    Neuronpedia

    INDEX
    Explanations

    representation, symbol, metaphor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    up
    0.94
    Ano
    0.80
     Infos
    0.79
    λε
    0.79
    coh
    0.78
    adv
    0.77
    ंबू
    0.76
     terd
    0.75
    مش
    0.75
     advocate
    0.74
    POSITIVE LOGITS
    ation
    0.96
    tive
    0.94
    ação
    0.87
    ing
    0.86
    ラル
    0.84
    اتی
    0.83
    ల్
    0.82
    ary
    0.80
    ATION
    0.78
    isku
    0.77
    Act Density 0.740%

    No Known Activations