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

    Neuronpedia

    INDEX
    Explanations

    code blocks with indentation

    oai_token-act-pair · gemini-2.0-flash

    seven

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.74
    endphp
    -0.68
    <?,
    -0.61
    ुनिया
    -0.60
    enseignements
    -0.59
     Italijani
    -0.59
     NSCoder
    -0.59
    ::_('
    -0.59
    UserScript
    -0.59
    GeneratedCode
    -0.56
    POSITIVE LOGITS
        
    0.52
     seven
    0.51
     SEVEN
    0.50
    7
    0.49
    omeness
    0.47
     Sieben
    0.45
    SEVEN
    0.43
    七
    0.43
     opérateur
    0.42
    seven
    0.42
    Act Density 0.935%

    No Known Activations