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

    Neuronpedia

    INDEX
    Explanations

    height

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric CSS dimension tokens (e.g., numbers with units like “100%,” “2.662109375,” “max‐width,” etc.), effectively spotting CSS size/value declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     свят
    -0.07
     پیشنه
    -0.06
    High
    -0.06
    _member
    -0.06
    مارات
    -0.06
    jobs
    -0.06
    Ja
    -0.06
     LoginPage
    -0.06
     вимог
    -0.06
    _fsm
    -0.06
    POSITIVE LOGITS
     extra
    0.06
    .orientation
    0.06
     correlates
    0.06
    тура
    0.06
     athleticism
    0.06
     score
    0.06
    ael
    0.06
     Theory
    0.06
     reli
    0.06
     tome
    0.06
    Act Density 0.011%

    No Known Activations