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

    Neuronpedia

    INDEX
    Explanations

    Forum posts

    np_max-act · gemini-2.0-flash

    This neuron detects words about contributing help or positive contributions (e.g. help, helping, offer, offering, bounty, answer, answers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ०
    -0.07
    RadioButton
    -0.07
    ora
    -0.06
     SIDE
    -0.06
     reporting
    -0.06
     discharged
    -0.06
     Wen
    -0.06
    (urls
    -0.06
     reliably
    -0.06
     Slut
    -0.06
    POSITIVE LOGITS
    сп
    0.07
     مفهوم
    0.07
     ::
    0.07
     plural
    0.07
     Βα
    0.06
    bib
    0.06
    propertyName
    0.06
    抑
    0.06
    opcode
    0.06
    elsif
    0.06
    Act Density 0.023%

    No Known Activations