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

    Neuronpedia

    INDEX
    Explanations

    "fmt

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -split
    -0.07
    _unique
    -0.07
     wan
    -0.07
     kiş
    -0.07
    Difference
    -0.07
    appen
    -0.07
    Latin
    -0.07
    𬹼
    -0.07
     cra
    -0.07
    .Symbol
    -0.07
    POSITIVE LOGITS
    组团
    0.07
     deprecated
    0.07
    玿
    0.07
    蝎
    0.06
    隺
    0.06
    生产工艺
    0.06
    ложить
    0.06
     stocked
    0.06
    ẻ
    0.06
    ousel
    0.06
    Act Density 0.030%

    No Known Activations