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

    Neuronpedia

    INDEX
    Explanations

    numeric values and parameters related to code or algorithms

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

    Numbers followed by commas or hyphens

    np_acts-logits-general · gemini-2.0-flash

    numerical lists and coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <=",
    -0.72
    ]--;
    -0.72
    ISupport
    -0.66
    ########.
    -0.64
    Parcelize
    -0.62
    brainly
    -0.60
    denly
    -0.58
    JvmStatic
    -0.58
     nakalista
    -0.56
    $}}
    -0.56
    POSITIVE LOGITS
    IntoConstraints
    0.65
    الحياه
    0.56
     opérés
    0.53
     Réponses
    0.52
    Indented
    0.50
     LoggerFactory
    0.49
     يتيمه
    0.48
    yntaxException
    0.46
    isContained
    0.46
    anim
    0.46
    Act Density 0.183%

    No Known Activations