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

    Neuronpedia

    INDEX
    Explanations

    ever

    np_max-act · gemini-2.0-flash

    This neuron activates on introductory, thought-provoking question phrases—especially “Have you ever …” or similar constructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     nim
    -0.06
     Carol
    -0.06
     nebude
    -0.06
    Carol
    -0.06
    °C
    -0.06
     Rodriguez
    -0.06
     encontrar
    -0.06
    Phi
    -0.06
     Kumar
    -0.06
     recru
    -0.06
    POSITIVE LOGITS
    QT
    0.07
     trabal
    0.07
    FFE
    0.07
    ={()
    0.06
     παρα
    0.06
    _ISS
    0.06
     불
    0.06
     closeButton
    0.06
    iface
    0.06
    ymce
    0.06
    Act Density 0.011%

    No Known Activations