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

    Neuronpedia

    INDEX
    Explanations

    syntax keywords and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    личные
    -0.82
     فى
    -0.81
    pañol
    -0.75
    tvrt
    -0.75
     hati
    -0.75
     AQUI
    -0.74
     kini
    -0.73
     pág
    -0.73
     morceau
    -0.73
    ọt
    -0.71
    POSITIVE LOGITS
    zené
    0.88
    restle
    0.83
     appearances
    0.82
    ཐ
    0.82
     aplicada
    0.80
     tachycardia
    0.80
    ()])
    0.79
     rheumatic
    0.79
     hlavy
    0.79
     amongst
    0.77
    Act Density 0.004%

    No Known Activations