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

    Neuronpedia

    INDEX
    Explanations

    Recommendations

    np_max-act · gemini-2.0-flash

    The neuron fires on audience-targeting recommendation phrases (e.g. “must-watch for fans,” “for everyone”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    epad
    -0.07
     freq
    -0.06
    .ONE
    -0.06
    .Request
    -0.06
    endants
    -0.06
    极
    -0.06
    (Field
    -0.06
     fins
    -0.06
    ':[
    -0.06
    UBY
    -0.06
    POSITIVE LOGITS
     beasts
    0.07
     doldur
    0.06
     ""
↵
    0.06
    زینه
    0.06
    	property
    0.06
     SelectListItem
    0.06
     Nielsen
    0.06
     elementos
    0.06
    dae
    0.06
    .intersection
    0.06
    Act Density 0.053%

    No Known Activations