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

    Neuronpedia

    INDEX
    Explanations

    lists of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    notlocked
    0.64
    pInBuffer
    0.61
     божо
    0.57
    nBitCount
    0.57
     vattum
    0.55
     RasterModelGrid
    0.54
    ))+\
    0.54
    ]=\
    0.53
    Strafpunkte
    0.53
     ferrugineux
    0.53
    POSITIVE LOGITS
    of
    0.63
     for
    0.61
     of
    0.58
      
    0.58
    in
    0.57
    H
    0.56
    T
    0.54
    W
    0.52
    S
    0.52
    for
    0.52
    Act Density 0.001%

    No Known Activations