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

    Neuronpedia

    INDEX
    Explanations

    mathematical/scientific equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IGGER
    -0.08
     imaginative
    -0.08
     جشن
    -0.08
     dwarf
    -0.08
     Isabelle
    -0.08
     cottage
    -0.08
    īg
    -0.07
    ell
    -0.07
    inecraft
    -0.07
     ympär
    -0.07
    POSITIVE LOGITS
     fitting
    0.09
     plot
    0.09
    lope
    0.09
     slope
    0.09
     fitted
    0.09
     correlation
    0.09
     enzyme
    0.09
     plots
    0.08
     intercept
    0.08
     correl
    0.08
    Act Density 0.004%

    No Known Activations