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

    Neuronpedia

    INDEX
    Explanations

    edit, editor, edition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.91
    ↵
    0.69
    CT
    0.68
    েন
    0.66
    انی
    0.66
    ক
    0.64
    یو
    0.61
    ב
    0.61
    IV
    0.59
    悩み
    0.59
    POSITIVE LOGITS
     Editar
    0.91
     редакти
    0.79
     编辑
    0.78
     реда
    0.77
     éd
    0.74
     Editing
    0.73
     편집
    0.70
    ма
    0.68
     образова
    0.66
    Editing
    0.66
    Act Density 0.022%

    No Known Activations