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

    Neuronpedia

    INDEX
    Explanations

    user paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    0.61
    ரச
    0.55
    す
    0.54
    воды
    0.54
    )=(\
    0.54
    OBJECT
    0.51
    DESCRIPTOR
    0.51
     hypersurface
    0.50
     मंत्रिपरिषद
    0.50
     whakap
    0.50
    POSITIVE LOGITS
    -
    0.81
    '
    0.67
     &
    0.61
    onaldo
    0.60
    ↵↵
    0.59
    /
    0.59
    en
    0.57
     at
    0.54
    eri
    0.54
    0.54
    Act Density 0.000%

    No Known Activations