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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (!__
    -0.94
     defaultstate
    -0.93
    OGND
    -0.91
     betweenstory
    -0.90
    AddTagHelper
    -0.89
    цездатний
    -0.87
    Rüyada
    -0.87
     للاسماء
    -0.86
     pinulongan
    -0.84
     intptr
    -0.83
    POSITIVE LOGITS
    fic
    0.52
    kjø
    0.48
    ACES
    0.48
    asure
    0.47
    nesse
    0.47
    ality
    0.46
    mesa
    0.46
    āv
    0.46
    hood
    0.46
    vén
    0.46
    Act Density 0.010%

    No Known Activations