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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    urate
    0.50
    Verse
    0.50
    AutoGen
    0.50
    Semaphore
    0.49
     کاربر
    0.48
    ون
    0.47
    CAL
    0.47
     Immac
    0.47
    VCT
    0.46
    ксана
    0.46
    POSITIVE LOGITS
     robbery
    0.47
     looting
    0.47
    ő
    0.45
     religious
    0.45
     hesitant
    0.45
     bien
    0.44
     robbing
    0.44
     baada
    0.43
    ورٹی
    0.43
     bandits
    0.43
    Act Density 0.001%

    No Known Activations