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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    didSet
    -0.67
    帖最后由
    -0.65
     <>",
    -0.62
    septic
    -0.59
    rangea
    -0.58
     Nog
    -0.57
    Tembelea
    -0.56
     Waray
    -0.56
    protoimpl
    -0.56
    ற்
    -0.55
    POSITIVE LOGITS
    PYX
    0.49
     internacionais
    0.49
    ines
    0.46
     estudos
    0.46
     cielos
    0.44
     الدولى
    0.44
     engraçadas
    0.43
    INES
    0.42
     pitié
    0.42
     étr
    0.42
    Act Density 0.000%

    No Known Activations