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

    Neuronpedia

    INDEX
    Explanations

    control and management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     attano
    0.43
     supplier
    0.41
     induce
    0.41
     receita
    0.41
     पचा
    0.41
     toxin
    0.40
     sábado
    0.39
     satiety
    0.39
     decode
    0.39
     kPa
    0.39
    POSITIVE LOGITS
    normalized
    0.41
     अधिव
    0.41
    ED
    0.39
    harmonic
    0.38
    лк
    0.38
    ENTE
    0.37
    STUD
    0.37
    ÉE
    0.37
    adiabatic
    0.37
     sorts
    0.37
    Act Density 0.000%

    No Known Activations