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

    Neuronpedia

    INDEX
    Explanations

    Sigma and Lean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     домашних
    -0.08
    *@
    -0.07
    orio
    -0.07
    jar
    -0.07
    Animate
    -0.07
    Con
    -0.06
    edii
    -0.06
    odon
    -0.06
    ной
    -0.06
    (Double
    -0.06
    POSITIVE LOGITS
     decorators
    0.07
     REALLY
    0.06
    Unless
    0.06
    blah
    0.06
     courageous
    0.06
     ace
    0.06
     extremely
    0.06
     뜻
    0.06
     XHTML
    0.06
     Put
    0.06
    Act Density 0.005%

    No Known Activations