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

    Neuronpedia

    INDEX
    Explanations

    opposite of existing objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تدائي
    0.45
    Vectors
    0.43
    يّ
    0.41
    ’
    0.41
     Webster
    0.40
    BibitemOpen
    0.40
    0.40
     Spokane
    0.39
    ystick
    0.39
    Webster
    0.39
    POSITIVE LOGITS
     М
    0.55
     ಮ
    0.55
    AxisSize
    0.54
     전쟁
    0.52
     ல
    0.51
     materiali
    0.51
     Х
    0.50
     ו
    0.49
     mapas
    0.49
     ל
    0.48
    Act Density 0.014%

    No Known Activations