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

    Neuronpedia

    INDEX
    Explanations

    understanding specific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    єднання
    0.48
    BooleanField
    0.45
     Ayn
    0.44
    adoras
    0.43
    avar
    0.42
    變
    0.41
    utils
    0.41
    setColor
    0.41
    checked
    0.41
    尽管
    0.41
    POSITIVE LOGITS
     isoforms
    0.45
    Vg
    0.44
    wso
    0.44
    lığı
    0.43
     offres
    0.42
     photospheric
    0.42
     anat
    0.42
     $'
    0.41
    Voc
    0.41
     stratification
    0.41
    Act Density 0.006%

    No Known Activations