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

    Neuronpedia

    INDEX
    Explanations

    commands and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     view
    -0.91
     View
    -0.83
    view
    -0.77
    曽
    -0.72
    lofen
    -0.66
    形象
    -0.66
     صفحه
    -0.65
    etta
    -0.65
    plist
    -0.63
    imageFile
    -0.63
    POSITIVE LOGITS
    PropTypes
    0.90
    ებ
    0.73
    msi
    0.72
    <0x84>
    0.72
     пальто
    0.71
    吲
    0.69
    Grant
    0.67
    السكان
    0.66
     Proverbs
    0.66
     thom
    0.66
    Act Density 0.073%

    No Known Activations