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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tions
    0.71
    些
    0.67
    徫
    0.66
     or
    0.66
     awa
    0.66
    ments
    0.65
     ç
    0.64
     ans
    0.64
     Geoff
    0.63
    犾
    0.63
    POSITIVE LOGITS
    imiento
    0.82
     машиналары
    0.79
    پار
    0.74
    avoro
    0.74
     cumpleaños
    0.73
     intentar
    0.73
     Arkadaşlar
    0.73
    ↳
    0.72
     prépuce
    0.71
    akty
    0.71
    Act Density 0.001%

    No Known Activations