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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron consistently activates on the word “to” when it introduces an infinitive (especially in expressions of intent or obligation, e.g. “had to be strong,” “time to…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    尋
    -0.07
     أكثر
    -0.07
     Settlement
    -0.06
    _setup
    -0.06
    είς
    -0.06
     Geme
    -0.06
     settlement
    -0.06
     intensity
    -0.06
     největší
    -0.06
     telah
    -0.06
    POSITIVE LOGITS
     rad
    0.07
    -padding
    0.07
    _at
    0.07
     �
    0.07
    	cnt
    0.06
    lg
    0.06
     avent
    0.06
    Off
    0.06
     GRAT
    0.06
     concat
    0.06
    Act Density 0.037%

    No Known Activations