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

    Neuronpedia

    INDEX
    Explanations

    quaint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betekent
    0.86
    ف
    0.73
    ↵↵
    0.70
     samme
    0.69
     moins
    0.68
     bodyguard
    0.68
     klasse
    0.68
     cinéma
    0.67
    pesar
    0.67
     stijl
    0.66
    POSITIVE LOGITS
    k
    0.94
    n
    0.93
    ה
    0.84
    ie
    0.82
     of
    0.78
    /
    0.76
    s
    0.73
    我们
    0.72
    ของ
    0.70
     antiqu
    0.69
    Act Density 0.001%

    No Known Activations