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

    Neuronpedia

    INDEX
    Explanations

    Separation/Distinction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     separating
    -1.08
     smell
    -0.77
    smell
    -0.60
     sépar
    -0.56
    eber
    -0.54
     فريبيس
    -0.53
    Between
    -0.51
     breakaway
    -0.50
     >=",
    -0.49
    sbereich
    -0.49
    POSITIVE LOGITS
    NameInMap
    0.72
     "..\..\
    0.71
    GRANTED
    0.70
    TintMode
    0.65
    ########.
    0.64
    WireFormatLite
    0.63
    EndInit
    0.62
     "..\..\..\
    0.61
    PerformLayout
    0.59
    réhen
    0.57
    Act Density 0.077%

    No Known Activations