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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    šten
    0.40
     här
    0.39
    倍
    0.38
    üge
    0.38
     Vicki
    0.37
     Clerk
    0.37
     elucidated
    0.36
    嬸
    0.36
     Darüber
    0.36
     verändert
    0.36
    POSITIVE LOGITS
    r
    0.42
    ალ
    0.42
    <0x0D>
    0.40
    ap
    0.39
     પસ
    0.38
    rary
    0.38
    rename
    0.37
    Xamarin
    0.37
    x
    0.37
    우
    0.36
    Act Density 0.000%

    No Known Activations