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

    Neuronpedia

    INDEX
    Explanations

    such

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “such.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _roll
    -0.07
     Harrison
    -0.07
     Fighters
    -0.07
    řes
    -0.07
     Dillon
    -0.07
    (area
    -0.06
     I
    -0.06
    arrison
    -0.06
     potatoes
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     such
    0.16
     Such
    0.11
    Such
    0.10
    such
    0.10
     SUCH
    0.10
     suche
    0.07
     авт
    0.07
     такий
    0.07
    schema
    0.06
    :{
    0.06
    Act Density 0.033%

    No Known Activations