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

    Neuronpedia

    INDEX
    Explanations

    therefore introducing a consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺔ
    1.16
    ряда
    1.15
    1
    1.13
    ١
    1.10
    ﻪ
    1.10
     matemáticas
    1.07
     parecido
    1.07
    ﺖ
    1.07
    ี
    1.03
    них
    1.02
    POSITIVE LOGITS
    ia
    1.17
     on
    0.98
    la
    0.97
    on
    0.95
    K
    0.95
    ↵
    0.93
    ano
    0.90
    ian
    0.89
    is
    0.87
     to
    0.86
    Act Density 0.049%

    No Known Activations