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

    Neuronpedia

    INDEX
    Explanations

    code, programming, or technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     মিস
    0.40
    FETCH
    0.37
    ディガン
    0.37
     quanta
    0.37
     baseUrl
    0.37
    wifi
    0.36
     aula
    0.36
     wifi
    0.36
    اویز
    0.36
     &:
    0.35
    POSITIVE LOGITS
    icación
    0.42
    uzten
    0.41
     nást
    0.40
     Resume
    0.39
     slecht
    0.39
     Quadro
    0.38
     Kräfte
    0.38
     கால
    0.38
    uptools
    0.38
     должно
    0.38
    Act Density 0.002%

    No Known Activations