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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron detects instances of the infinitive marker “to” when it introduces a following verb.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    yh
    -0.07
     Keith
    -0.07
     비교
    -0.07
     organised
    -0.06
    	cursor
    -0.06
     iterating
    -0.06
    Azure
    -0.06
    Restaurant
    -0.06
    كور
    -0.06
     KA
    -0.06
    POSITIVE LOGITS
    =w
    0.06
     ligne
    0.06
    AM
    0.06
    _mini
    0.06
    HOST
    0.06
    abwe
    0.05
    thresh
    0.05
     imb
    0.05
    _cut
    0.05
    :'#
    0.05
    Act Density 0.063%

    No Known Activations