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

    Neuronpedia

    INDEX
    Explanations

    titles and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (coder
    -0.07
    (colors
    -0.06
     packaging
    -0.06
     νέ
    -0.06
    plugins
    -0.06
     پن
    -0.06
     Sap
    -0.06
    _PROTOCOL
    -0.06
     Jeg
    -0.06
    .ident
    -0.06
    POSITIVE LOGITS
    Printf
    0.07
    iego
    0.07
    }.
    0.07
    ("/")
    0.06
    Ђ
    0.06
     JAXB
    0.06
    99
    0.06
     legitimate
    0.06
    639
    0.06
    MERCHANTABILITY
    0.06
    Act Density 0.109%

    No Known Activations