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

    Neuronpedia

    INDEX
    Explanations

    progress made

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺭ
    2.00
    ﻭ
    1.95
    ı
    1.88
    oglycos
    1.51
     След
    1.50
    ，
    1.49
    时候
    1.48
     sentencia
    1.47
    ты
    1.43
     merupakan
    1.37
    POSITIVE LOGITS
    ون
    2.16
    ות
    1.63
    sx
    1.63
    ра
    1.48
    itung
    1.46
    ്‍
    1.44
    ิค
    1.39
    ッド
    1.38
     Chicks
    1.35
    ै
    1.33
    Act Density 0.007%

    No Known Activations