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

    Neuronpedia

    INDEX
    Explanations

    code changes intended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     klasy
    0.43
     ไง
    0.42
    आईओएस
    0.42
    isDebug
    0.42
     mädchen
    0.42
    fab
    0.41
    btw
    0.41
    adena
    0.41
     μεγαλ
    0.41
    BitCount
    0.41
    POSITIVE LOGITS
    ructions
    0.46
     Sush
    0.46
     Injuries
    0.46
    entino
    0.43
     nerfs
    0.42
     Dosage
    0.41
    -
    0.41
    об
    0.41
    一丝
    0.41
     Appe
    0.40
    Act Density 0.003%

    No Known Activations