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

    Neuronpedia

    INDEX
    Explanations

    code and web snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pectrum
    -0.08
    Escape
    -0.07
     meng
    -0.07
    ='-
    -0.07
    稣
    -0.06
    תיב
    -0.06
    .isUser
    -0.06
    enguins
    -0.06
    以為
    -0.06
    iever
    -0.06
    POSITIVE LOGITS
    ados
    0.07
    诋
    0.07
    本市
    0.07
    /logs
    0.07
     balloon
    0.07
    _processed
    0.07
    省教育
    0.07
     Babies
    0.07
    辆
    0.07
    elligence
    0.07
    Act Density 0.000%

    No Known Activations