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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    amentos
    -0.08
     Highest
    -0.07
     reducer
    -0.07
     Permit
    -0.07
     cup
    -0.07
     dú
    -0.07
    multiple
    -0.07
    entes
    -0.06
    _GF
    -0.06
    ETH
    -0.06
    POSITIVE LOGITS
    キャラ
    0.08
    �
    0.07
     łaz
    0.07
     위해
    0.07
     FindObjectOfType
    0.07
     חיי
    0.07
    されること
    0.06
     annoying
    0.06
    _UART
    0.06
    点燃
    0.06
    Act Density 0.001%

    No Known Activations