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

    Neuronpedia

    INDEX
    Explanations

    structs, types, and namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     secara
    1.90
     létre
    1.84
    orbits
    1.81
     pesos
    1.75
    mysqli
    1.72
     withholding
    1.71
     historiques
    1.68
     включа
    1.66
     usług
    1.65
    ෙන්
    1.63
    POSITIVE LOGITS
    a
    1.52
    ia
    1.43
    te
    1.41
    io
    1.39
    ure
    1.38
    اا
    1.38
    olta
    1.37
    ا
    1.36
    ie
    1.33
    icine
    1.31
    Act Density 0.048%

    No Known Activations