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

    Neuronpedia

    INDEX
    Explanations

    International Protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     popolo
    0.38
     erzählt
    0.37
     Сою
    0.37
     Kampf
    0.36
     natoque
    0.36
    cesz
    0.36
    зию
    0.36
     биографи
    0.36
    ources
    0.36
    zesz
    0.36
    POSITIVE LOGITS
     conduction
    0.42
     twist
    0.41
    getRequest
    0.41
     exceptions
    0.40
     exception
    0.40
     conduct
    0.39
     protected
    0.39
     ক্ষমা
    0.39
     Protection
    0.38
    kada
    0.38
    Act Density 0.000%

    No Known Activations