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

    Neuronpedia

    INDEX
    Explanations

    field

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iverso
    1.08
    t
    1.07
    elter
    1.05
    uya
    1.05
    adə
    1.04
    ت
    1.04
    erp
    1.02
    iring
    1.01
     cuff
    1.00
    eru
    1.00
    POSITIVE LOGITS
    ਾ
    1.24
    ное
    1.23
    ες
    1.15
     தன்மை
    1.09
     capazes
    1.03
     appell
    1.02
    тол
    1.02
     Planes
    1.01
    दे
    1.00
     एसएस
    1.00
    Act Density 0.004%

    No Known Activations