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

    Neuronpedia

    INDEX
    Explanations

    management and other categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intento
    0.49
     arise
    0.48
     asked
    0.48
     unteren
    0.48
     நெரு
    0.46
     offenen
    0.46
     etwa
    0.46
     Increased
    0.46
     setzt
    0.45
     aiuto
    0.45
    POSITIVE LOGITS
    ключа
    0.49
    یو
    0.46
    ก
    0.46
    кая
    0.45
    سان
    0.44
    쿰
    0.42
    тит
    0.42
    प्या
    0.42
    고
    0.42
    दर्श
    0.41
    Act Density 0.001%

    No Known Activations