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

    Neuronpedia

    INDEX
    Explanations

    titles and themes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bên
    0.92
     mặt
    0.91
     Sebagai
    0.89
    ﾏ
    0.85
     Jeder
    0.85
    <unused2106>
    0.84
     Thế
    0.83
     একটা
    0.83
     Neces
    0.83
    একটা
    0.82
    POSITIVE LOGITS
    noir
    0.72
    Sync
    0.71
    azepam
    0.71
    说法
    0.69
    ouilles
    0.67
    Equations
    0.67
    Spl
    0.67
     Gaga
    0.66
    XS
    0.66
    佯
    0.66
    Act Density 0.101%

    No Known Activations