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

    Neuronpedia

    INDEX
    Explanations

    code example explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অবসর
    0.64
    이번
    0.60
    iqi
    0.60
     weekdays
    0.59
    DataType
    0.59
    িত্ত
    0.59
    pure
    0.58
    omerang
    0.58
     টাইমস
    0.58
     Pure
    0.58
    POSITIVE LOGITS
     tycker
    1.05
     skriv
    0.90
     Har
    0.87
     behöver
    0.87
     synes
    0.86
     taki
    0.86
     Nej
    0.84
     tror
    0.83
    Jeg
    0.82
     Monter
    0.81
    Act Density 0.046%

    No Known Activations