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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.87
     OnInit
    -0.68
     petitions
    -0.66
    Personendaten
    -0.66
    Lähteet
    -0.65
    ConverterFactory
    -0.63
     onCancelled
    -0.63
    rawDesc
    -0.63
     coils
    -0.60
    Fotó
    -0.59
    POSITIVE LOGITS
     square
    0.54
    ItemBackground
    0.52
     cet
    0.46
    corns
    0.44
    chaun
    0.44
     Square
    0.44
    OVERN
    0.43
    %]
    0.43
     autorytatywna
    0.43
    square
    0.42
    Act Density 0.001%

    No Known Activations