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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash

    This neuron detects the occurrence of the word “factually.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Footer
    -0.06
    VM
    -0.06
    ascar
    -0.06
     perennial
    -0.06
    assel
    -0.06
     peanuts
    -0.06
     Slide
    -0.06
     Copenhagen
    -0.06
     Democrat
    -0.06
    上
    -0.06
    POSITIVE LOGITS
     ([]
    0.07
    ятия
    0.07
    ститут
    0.06
    .Cursors
    0.06
    ellation
    0.06
     田
    0.06
    der
    0.06
     fraught
    0.06
     quarry
    0.06
    /arm
    0.06
    Act Density 0.001%

    No Known Activations