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

    Neuronpedia

    INDEX
    Explanations

    neck, Fn, not, Main, who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Are
    0.99
     A
    0.93
     What
    0.92
     Idi
    0.91
     Ian
    0.91
     IA
    0.91
    o
    0.90
     It
    0.89
     Yup
    0.88
     Curr
    0.88
    POSITIVE LOGITS
    પાસ
    0.95
     réseau
    0.87
     мозга
    0.83
     escritório
    0.82
     koul
    0.81
    akta
    0.81
     família
    0.79
     revisão
    0.79
     théra
    0.79
     güç
    0.79
    Act Density 0.000%

    No Known Activations