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

    Neuronpedia

    INDEX
    Explanations

    @ prefixed code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     s
    0.63
    er
    0.55
     tuo
    0.52
     t
    0.52
     sheriff
    0.52
     recovery
    0.52
    i
    0.52
    Y
    0.52
     mau
    0.50
     saud
    0.50
    POSITIVE LOGITS
     Gerais
    0.57
    只限平日
    0.57
    sons
    0.54
    OHN
    0.53
    ្ស
    0.52
    कुछ
    0.52
    не
    0.52
     یورپی
    0.52
     Unternehmens
    0.51
     Estudio
    0.51
    Act Density 0.000%

    No Known Activations