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

    Neuronpedia

    INDEX
    Explanations

    code import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RIQUE
    -0.49
     of
    -0.46
    '
    -0.44
     X
    -0.44
    డ్
    -0.43
    name
    -0.43
    鲜
    -0.43
    ’
    -0.43
    AIRES
    -0.43
    вест
    -0.43
    POSITIVE LOGITS
     Roskov
    0.76
    stateProvider
    0.75
    SharedDtor
    0.70
    AnchorStyles
    0.68
    onViewCreated
    0.66
     виправивши
    0.66
    پیوند
    0.66
     becauſe
    0.66
    +#+#
    0.65
    EReference
    0.63
    Act Density 0.005%

    No Known Activations