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

    Neuronpedia

    INDEX
    Explanations

    breaks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Assertions
    -0.07
     ancestor
    -0.07
     loc
    -0.07
     ListNode
    -0.07
    Fee
    -0.06
    Restr
    -0.06
    학교
    -0.06
     Encoder
    -0.06
     cone
    -0.06
     ministers
    -0.06
    POSITIVE LOGITS
    �
    0.07
     ([]
    0.07
     ов
    0.06
     سیستم
    0.06
    _pct
    0.06
    REFERENCES
    0.06
    muş
    0.06
     Fargo
    0.06
    股
    0.06
    ffects
    0.06
    Act Density 0.019%

    No Known Activations