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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     justicia
    -0.08
     hemis
    -0.08
     Forbidden
    -0.08
     lounge
    -0.08
     forbidden
    -0.08
    Forbidden
    -0.07
    ен
    -0.07
     visor
    -0.07
     тура
    -0.07
    .just
    -0.07
    POSITIVE LOGITS
     uppt
    0.09
     exhaustion
    0.09
     trailing
    0.09
     tallest
    0.08
    Trailing
    0.08
     présence
    0.08
     busiest
    0.08
     VBA
    0.08
     determining
    0.08
     মৃত
    0.08
    Act Density 0.004%

    No Known Activations