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

    Neuronpedia

    INDEX
    Explanations

    undo and retry operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geospatial
    0.77
     biodiversity
    0.74
     geograf
    0.71
     prospecting
    0.70
     ethnographic
    0.70
     visionary
    0.69
     worldview
    0.69
     Smithsonian
    0.69
     ethnicity
    0.68
     labrador
    0.67
    POSITIVE LOGITS
    Undo
    1.03
     Retry
    0.86
     glPopMatrix
    0.82
     undo
    0.82
     Undo
    0.81
     backtracking
    0.74
    ﺮ
    0.74
    undo
    0.73
    ស្រាយ
    0.73
    缓存
    0.71
    Act Density 1.639%

    No Known Activations