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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invalidate
    -0.07
     hazard
    -0.07
    fmt
    -0.06
     Tut
    -0.06
    níkem
    -0.06
    fq
    -0.06
     обращ
    -0.06
    _bitmap
    -0.06
    opt
    -0.06
    andes
    -0.06
    POSITIVE LOGITS
     примен
    0.07
     Slug
    0.07
     digestion
    0.06
    _pct
    0.06
    (""+
    0.06
    妖
    0.06
    (Code
    0.06
     trận
    0.06
    тів
    0.06
    官网
    0.06
    Act Density 0.024%

    No Known Activations