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

    Neuronpedia

    INDEX
    Explanations

    delimiters

    np_max-act · gemini-2.0-flash

    The neuron is specialized for spotting the bullet‐list structure in the form, i.e. the list‐item markers (like “*”) and the template field tokens (e.g. “NAME_” or “Col(lected)”) that appear at the start of each bullet.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    кар
    -0.07
    RecyclerView
    -0.06
     Apache
    -0.06
    sea
    -0.06
    uran
    -0.06
    .finish
    -0.06
    یات
    -0.06
    klä
    -0.06
     Capcom
    -0.06
    -categories
    -0.06
    POSITIVE LOGITS
    ,data
    0.07
     setDate
    0.06
    arians
    0.06
    ((&___
    0.06
     onFocus
    0.06
    ainted
    0.06
     technician
    0.06
    .Fields
    0.06
    ：</
    0.06
     cheeks
    0.06
    Act Density 0.009%

    No Known Activations