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

    Neuronpedia

    INDEX
    Explanations

    programming file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     folder
    0.80
     Folder
    0.71
    内容的
    0.71
     corridor
    0.70
     folders
    0.68
    📂
    0.67
     rectified
    0.67
     restructured
    0.66
     concatenated
    0.66
     relativa
    0.65
    POSITIVE LOGITS
     तत्
    0.82
    extension
    0.80
    extensions
    0.77
    Extension
    0.77
     extension
    0.76
     확
    0.75
     Extension
    0.72
     ciências
    0.69
     রজ
    0.69
     Erweiter
    0.69
    Act Density 0.051%

    No Known Activations