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

    Neuronpedia

    INDEX
    Explanations

    -N

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numeric tokens (e.g. years, version numbers, port numbers, or other multi-digit values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Tan
    -0.07
     tempered
    -0.06
     dic
    -0.06
    .userInfo
    -0.06
     bullying
    -0.06
    alerts
    -0.06
     normalize
    -0.06
     morality
    -0.06
     setPosition
    -0.06
    luví
    -0.06
    POSITIVE LOGITS
     Tactics
    0.07
    _growth
    0.07
     boats
    0.07
     작성
    0.07
     voiture
    0.06
    ῦ
    0.06
     sobie
    0.06
     entren
    0.06
    ereg
    0.06
    Scores
    0.06
    Act Density 0.137%

    No Known Activations