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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the phrase “without replacement.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ,nil
    -0.07
     Correction
    -0.07
     still
    -0.06
    騎
    -0.06
    是在
    -0.06
     skate
    -0.06
    al
    -0.06
    ::::
    -0.06
     three
    -0.06
     healing
    -0.06
    POSITIVE LOGITS
     uzavř
    0.07
    (Mouse
    0.07
     požadav
    0.06
    exao
    0.06
     Post
    0.06
     Công
    0.06
     minimise
    0.06
     Во
    0.06
    dex
    0.06
    raphics
    0.06
    Act Density 0.001%

    No Known Activations