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

    Neuronpedia

    INDEX
    Explanations

    code variables and list/array notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plupart
    0.29
     autre
    0.26
     fenó
    0.26
     دوسروں
    0.26
     двох
    0.25
     blanchâtre
    0.25
     altro
    0.24
     nghĩ
    0.23
     druhé
    0.23
     své
    0.23
    POSITIVE LOGITS
    ist
    0.33
    iste
    0.30
    istem
    0.29
    ’
    0.29
    ists
    0.28
    ays
    0.27
    .
    0.27
    ors
    0.27
    istic
    0.26
    <0xEF>
    0.26
    Act Density 0.353%

    No Known Activations