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

    Neuronpedia

    INDEX
    Explanations

    now, yet, anymore, either

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺘ
    1.24
     Ivanov
    1.16
    𝓲
    1.15
    ﯽ
    1.10
     údaje
    1.09
    𝓸
    1.08
    ர்
    1.05
    i
    1.05
    ﻲ
    1.05
    ليزية
    1.03
    POSITIVE LOGITS
    ال
    1.07
    '
    0.94
    ה
    0.93
    кратно
    0.91
    }
    0.90
    A
    0.90
     THE
    0.89
    כ
    0.89
    $
    0.87
    Tact
    0.86
    Act Density 0.116%

    No Known Activations