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

    Neuronpedia

    INDEX
    Explanations

    Code/terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Alex
    -0.07
     lun
    -0.07
     OSI
    -0.07
     spyOn
    -0.07
    projection
    -0.06
    _UNKNOWN
    -0.06
    onChange
    -0.06
    -0.06
    μιο
    -0.06
    gift
    -0.06
    POSITIVE LOGITS
    ire
    0.07
    يدا
    0.06
    ा↵↵
    0.06
    heels
    0.06
    _tbl
    0.06
     */↵
    0.06
    鱼
    0.06
    ودة
    0.06
    ίνα
    0.06
     svc
    0.06
    Act Density 0.000%

    No Known Activations