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

    Neuronpedia

    INDEX
    Explanations

    IGHT

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🌄
    -0.07
    atty
    -0.07
     Hope
    -0.07
    醫生
    -0.07
    擔心
    -0.06
     işçi
    -0.06
    "context
    -0.06
     الوطن
    -0.06
    %),
    -0.06
     carriers
    -0.06
    POSITIVE LOGITS
    ┼
    0.07
    _Find
    0.07
    FieldName
    0.07
    视察
    0.07
    chet
    0.07
    Stamp
    0.07
    _Start
    0.07
    柄
    0.07
    _BITS
    0.07
     persec
    0.07
    Act Density 0.001%

    No Known Activations