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

    Neuronpedia

    INDEX
    Explanations

    phrases and code snippets related to programming errors and exceptions

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

    Mathematical or chemical formulas/expressions

    np_acts-logits-general · gemini-2.0-flash

    technical and scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    حياته
    -0.71
    GEBURTS
    -0.60
    neſs
    -0.57
     Araujo
    -0.54
    addCriterion
    -0.53
    דיה
    -0.52
    abestanden
    -0.52
    ſhip
    -0.51
    حياتها
    -0.50
    Життєпис
    -0.49
    POSITIVE LOGITS
     digress
    0.89
    ))),
    0.85
    fromnode
    0.84
    TagMode
    0.80
    ])),
    0.80
    setVerticalGroup
    0.77
    )))))
    0.75
    ())),
    0.75
    )."
    0.74
    ))).
    0.71
    Act Density 2.983%

    No Known Activations