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

    Neuronpedia

    INDEX
    Explanations

    the names of classes and functions in code.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     @"/
    -0.63
    +#+#
    -0.53
     mergeFrom
    -0.51
    ⓧ
    -0.49
     gelungen
    -0.47
    ща
    -0.46
    BorderWidth
    -0.45
     незавершена
    -0.45
     отношению
    -0.44
     buoni
    -0.43
    POSITIVE LOGITS
    存于互联网档案馆
    0.79
    最快更新
    0.69
    MemoryWarning
    0.61
     الاطلاع
    0.59
    AxisAlignment
    0.58
    PerformLayout
    0.57
    日閲覧
    0.57
    ombres
    0.56
    NUMX
    0.54
     Baillargeon
    0.54
    Act Density 1.408%

    No Known Activations