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

    Neuronpedia

    INDEX
    Explanations

    splitting text with delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    G
    1.32
    R
    1.17
    H
    1.16
    S
    1.14
    D
    1.14
    C
    1.13
    L
    1.10
    U
    1.05
    K
    1.05
    З
    0.98
    POSITIVE LOGITS
    ين
    0.90
    し
    0.77
    ير
    0.74
     sinistra
    0.74
    يريا
    0.74
    ,$$
    0.73
     messa
    0.73
    してます
    0.71
     trat
    0.71
     adicionar
    0.71
    Act Density 0.001%

    No Known Activations