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

    Neuronpedia

    INDEX
    Explanations

    normalizing constant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ὑ
    0.29
     ڕۆ
    0.29
     Cré
    0.28
     ἀ
    0.28
     référence
    0.28
     विश्लेषण
    0.27
     équ
    0.26
     Zustimmung
    0.26
     Prés
    0.26
     punctatis
    0.26
    POSITIVE LOGITS
    e
    0.30
    р
    0.28
    wood
    0.27
    েক
    0.25
     kleiner
    0.25
    although
    0.24
    том
    0.24
    if
    0.24
    smaller
    0.24
    ates
    0.24
    Act Density 0.000%

    No Known Activations