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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Harmony
    -0.07
    ologists
    -0.07
     CMS
    -0.07
     devout
    -0.07
    Function
    -0.07
     democracy
    -0.06
    atology
    -0.06
    �
    -0.06
     cultivation
    -0.06
    atasets
    -0.06
    POSITIVE LOGITS
     ख
    0.07
     agre
    0.06
     vidéo
    0.06
    tı
    0.06
    “He
    0.06
     질
    0.06
    page
    0.06
    Quote
    0.06
    stdout
    0.06
    $(".
    0.06
    Act Density 0.090%

    No Known Activations