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

    Neuronpedia

    INDEX
    Explanations

    language translation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     académica
    0.48
     principalmente
    0.45
     vyu
    0.44
     pengurangan
    0.44
     disminución
    0.43
     divino
    0.41
     méthod
    0.40
     tecnológico
    0.40
     tecnológica
    0.40
     versus
    0.39
    POSITIVE LOGITS
    at
    0.48
    碑
    0.44
    anagram
    0.41
    et
    0.41
    ное
    0.41
     создать
    0.40
     транспорт
    0.39
    ര
    0.39
    Hotel
    0.39
    ו
    0.39
    Act Density 0.003%

    No Known Activations