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

    Neuronpedia

    INDEX
    Explanations

    numbers and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seamlessly
    0.44
    ția
    0.42
    чена
    0.42
     agency
    0.41
     nac
    0.41
     技术
    0.40
    ämm
    0.40
     prot
    0.39
     administrative
    0.39
     이용
    0.39
    POSITIVE LOGITS
     "?"
    0.46
     जॉर्ज
    0.45
    萼
    0.44
    Truthy
    0.43
     justifica
    0.43
    Expensive
    0.42
    吟
    0.42
    োহর
    0.41
    Charset
    0.41
    ;"
    0.41
    Act Density 0.000%

    No Known Activations