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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ശിവ
    0.41
    त्न
    0.39
     present
    0.37
    preload
    0.36
    ُو
    0.36
    로부터
    0.36
    轼
    0.35
    राज
    0.35
     interests
    0.35
     زیر
    0.34
    POSITIVE LOGITS
    alliative
    0.40
    ┈┈
    0.39
    ========
    0.37
    ത്തിലെ
    0.37
    dote
    0.37
    clientX
    0.37
    alq
    0.37
    balancing
    0.36
    insuff
    0.36
     Cruise
    0.36
    Act Density 0.001%

    No Known Activations