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

    Neuronpedia

    INDEX
    Explanations

    references to iconic or famous elements and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    famous or iconic examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.44
     للمعارف
    -0.41
    dicionado
    -0.37
    Multiple
    -0.37
    szy
    -0.36
    ूरत
    -0.36
     Multiple
    -0.35
    ścioła
    -0.35
    Sicher
    -0.35
    Secured
    -0.35
    POSITIVE LOGITS
     famous
    1.09
    famous
    0.95
    Famous
    0.86
     Famous
    0.85
     iconic
    0.84
     famously
    0.80
     berühmten
    0.79
     legendary
    0.78
     famosa
    0.77
     famosos
    0.77
    Act Density 0.107%

    No Known Activations