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

    Neuronpedia

    INDEX
    Explanations

    colegas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nél
    1.10
    ine
    1.07
    ation
    1.06
    ید
    0.97
    ip
    0.97
     not
    0.93
    government
    0.93
    n
    0.92
    ach
    0.89
    als
    0.88
    POSITIVE LOGITS
     a
    1.36
    ма
    0.96
     radionu
    0.91
     في
    0.90
    كا
    0.88
    كل
    0.87
     reales
    0.86
     براي
    0.86
     ezzel
    0.85
    ك
    0.85
    Act Density 0.042%

    No Known Activations