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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     fins
    1.22
     ACT
    1.19
     crosses
    1.17
    icles
    1.11
     Πολ
    1.11
    期限
    1.08
    Seconds
    1.07
     actu
    1.07
     sep
    1.04
     গতি
    1.03
    POSITIVE LOGITS
     Izv
    1.22
    ं
    1.11
    embod
    1.10
    benchmark
    1.09
    plural
    1.07
    Ü
    1.06
    openjdk
    1.06
    ্যোগ
    1.05
    နေ့
    1.05
    ̇
    1.03
    Act Density 0.000%

    No Known Activations