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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    The neuron responds to present‐participle (–ing) verbs that name ongoing actions or operations (e.g. “nesting,” “using,” “engaging,” “connecting”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    guide
    -0.07
     UITableViewDelegate
    -0.07
    .hstack
    -0.07
    .animations
    -0.07
     PropertyValue
    -0.07
    	assert
    -0.06
    ,state
    -0.06
    Expose
    -0.06
    asuring
    -0.06
    ahn
    -0.06
    POSITIVE LOGITS
     ист
    0.07
     섬
    0.06
     THAN
    0.06
     gén
    0.06
     Charm
    0.06
    'ét
    0.06
    Bin
    0.06
     besten
    0.06
     کری
    0.06
    SEQ
    0.06
    Act Density 0.052%

    No Known Activations