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

    Neuronpedia

    INDEX
    Explanations

    Location and Education

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lud
    -0.07
     deity
    -0.06
    ++;↵
    -0.06
     outlet
    -0.06
    5
    -0.06
    .condition
    -0.06
    _forward
    -0.06
    ontent
    -0.06
    宜
    -0.06
    孩子
    -0.06
    POSITIVE LOGITS
     WN
    0.07
    kr
    0.07
     ژ
    0.06
     понима
    0.06
     deneyim
    0.06
    olvers
    0.06
    틀
    0.06
     AVR
    0.06
     那
    0.06
     PF
    0.06
    Act Density 0.025%

    No Known Activations