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

    Neuronpedia

    INDEX
    Explanations

    foreign language characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theorists
    0.49
     corps
    0.48
     Communists
    0.47
     precincts
    0.44
    ړو
    0.43
     digress
    0.43
     fermions
    0.43
     Goes
    0.42
     PHY
    0.42
     جوړونکو
    0.41
    POSITIVE LOGITS
    д
    0.53
    ı
    0.49
    я
    0.47
    MP
    0.46
    à
    0.45
    re
    0.44
     свободно
    0.44
    ра
    0.43
     послу
    0.42
     форма
    0.42
    Act Density 0.000%

    No Known Activations