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

    Neuronpedia

    INDEX
    Explanations

    image and network operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cllr
    0.37
    ızı
    0.35
    ěn
    0.34
    󠁧
    0.33
    ą
    0.33
    lx
    0.32
    itemap
    0.32
     kz
    0.32
    spacerItem
    0.31
    吣
    0.31
    POSITIVE LOGITS
    WaitGroup
    0.33
     पंच
    0.32
    鉅
    0.31
     ALERT
    0.31
     Robins
    0.30
     ABC
    0.30
    iddag
    0.29
    ওয়ায়
    0.29
     Commit
    0.28
    Alert
    0.28
    Act Density 0.017%

    No Known Activations