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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron activates on the comparative phrase “instead of,” i.e. tokens forming the “instead of” construction.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     everytime
    -0.07
     Ngày
    -0.07
    .On
    -0.06
    mutations
    -0.06
     day
    -0.06
    ریه
    -0.06
    dm
    -0.06
     convinced
    -0.06
     DAY
    -0.06
    opro
    -0.06
    POSITIVE LOGITS
    (hdc
    0.07
     vědom
    0.07
     Philly
    0.07
    äl
    0.06
    	export
    0.06
     cra
    0.06
     cauliflower
    0.06
    \\/
    0.06
    +=(
    0.06
    POOL
    0.06
    Act Density 0.005%

    No Known Activations