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

    Neuronpedia

    INDEX
    Explanations

    code snippets, especially those with control flow structures

    oai_token-act-pair · gemini-2.0-flash

    rare terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nickname
    -0.42
    reg
    -0.42
    glyphicon
    -0.41
     Cla
    -0.40
    alignItems
    -0.40
     súng
    -0.40
    юй
    -0.40
     CL
    -0.40
    மை
    -0.40
    ⓧ
    -0.39
    POSITIVE LOGITS
    WithIOException
    0.91
     Theſe
    0.83
    CreateModel
    0.75
     Мексичка
    0.73
    OGND
    0.73
    Rujuakan
    0.71
    :✨
    0.71
    
    0.71
    SourceChecksum
    0.71
    日閲覧
    0.70
    Act Density 7.097%

    No Known Activations