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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens (e.g. integers or floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ninth
    -0.07
     again
    -0.07
     mars
    -0.07
     дея
    -0.06
     material
    -0.06
    itals
    -0.06
    (Session
    -0.06
    Granted
    -0.06
    goal
    -0.06
     mates
    -0.06
    POSITIVE LOGITS
     volte
    0.07
    μο
    0.07
     Charlie
    0.06
     cleansing
    0.06
    _CHARS
    0.06
    _palette
    0.06
    Illustr
    0.05
     colonial
    0.05
    �
    0.05
     �
    0.05
    Act Density 0.038%

    No Known Activations