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

    Neuronpedia

    INDEX
    Explanations

    Too much effort/complexity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sve
    -0.08
     Sunshine
    -0.07
    ावी
    -0.07
     communicates
    -0.07
     remarkably
    -0.07
     Hep
    -0.07
     complex
    -0.07
     thrive
    -0.07
     Mediterranean
    -0.07
     Stevenson
    -0.07
    POSITIVE LOGITS
     unless
    0.10
     بالنسبة
    0.09
    unless
    0.08
     demais
    0.08
    ٠
    0.08
     unnecessary
    0.08
    CURRENT
    0.08
     beasts
    0.08
     :(
    0.08
    0.08
    Act Density 0.017%
    No Known Activations