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

    Neuronpedia

    INDEX
    Explanations

    key terms and their context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iyaç
    0.43
     поговорим
    0.40
    0.40
     pantalla
    0.38
     порт
    0.38
    Sad
    0.37
    melidir
    0.35
     unidad
    0.35
    길
    0.35
     привет
    0.35
    POSITIVE LOGITS
    nato
    0.40
    jaro
    0.39
    rooted
    0.39
    Indexed
    0.38
    無料
    0.38
     decay
    0.38
     immortality
    0.38
     indexed
    0.37
    numpy
    0.37
    hauser
    0.37
    Act Density 0.000%

    No Known Activations