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

    Neuronpedia

    INDEX
    Explanations

    essay ESA UN desa pesos OSA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    1.63
    िया
    1.48
    し
    1.42
    िक
    1.38
    م
    1.36
    as
    1.27
    ून
    1.17
    ী
    1.16
    to
    1.16
    وم
    1.14
    POSITIVE LOGITS
     ."
    1.29
     as
    1.28
    ↵↵
    1.27
    IP
    1.23
    AR
    1.21
    ς
    1.20
     Балтбет
    1.20
     canción
    1.19
     is
    1.18
     распростран
    1.16
    Act Density 0.048%

    No Known Activations