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

    Neuronpedia

    INDEX
    Explanations

    Code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出版年
    -0.97
    ⓧ
    -0.83
    __':
    -0.77
    __":
    -0.72
    setVerticalGroup
    -0.65
    Zunanje
    -0.64
     Wicidata
    -0.63
    __':
    -0.63
    RunWith
    -0.62
     cref
    -0.62
    POSITIVE LOGITS
     have
    0.50
     avoir
    0.45
     since
    0.43
     teria
    0.42
    etCode
    0.42
     has
    0.41
    oprop
    0.41
    ContextHolder
    0.39
    Tpl
    0.39
     habría
    0.38
    Act Density 0.000%

    No Known Activations