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

    Neuronpedia

    INDEX
    Explanations

    safe and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     של
    0.30
     \{
    0.29
     của
    0.29
    </sup>
    0.28
    }$.
    0.27
     Ở
    0.27
     utilisent
    0.27
     appartiennent
    0.27
    Το
    0.27
     +(
    0.27
    POSITIVE LOGITS
     and
    0.47
    izing
    0.32
    -
    0.32
    ley
    0.29
    ifying
    0.29
    性和
    0.29
    、
    0.28
     thoughtful
    0.27
     high
    0.27
    istically
    0.27
    Act Density 0.504%

    No Known Activations