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

    Neuronpedia

    INDEX
    Explanations

    model technical terms and their features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.30
     něj
    0.30
    ম
    0.30
    э
    0.30
    İ
    0.30
    或其他
    0.28
    (\
    0.27
    म
    0.27
    讯
    0.27
    ES
    0.26
    POSITIVE LOGITS
     idiosync
    0.36
    xiety
    0.33
     kaos
    0.32
    schutz
    0.32
     consecuencias
    0.32
     confusión
    0.32
     typu
    0.31
     autonomia
    0.31
    خرى
    0.31
     différences
    0.31
    Act Density 0.032%

    No Known Activations