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

    Neuronpedia

    INDEX
    Explanations

    `.exe` command line arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    -1.98
    P
    -1.91
    D
    -1.87
    F
    -1.82
    M
    -1.82
    B
    -1.80
    T
    -1.74
    E
    -1.69
    C
    -1.68
    d
    -1.67
    POSITIVE LOGITS
    Nya
    1.53
    samt
    1.52
    Grafik
    1.51
    Kval
    1.50
    Makan
    1.48
     triko
    1.48
    Kek
    1.48
    1.48
    Cek
    1.48
    geç
    1.45
    Act Density 0.007%

    No Known Activations