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

    Neuronpedia

    INDEX
    Explanations

    Yes

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “Yes” at the start of affirmative assistant replies.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    _apply
    -0.07
     USHORT
    -0.07
    076
    -0.07
     приблиз
    -0.06
     recur
    -0.06
    .stat
    -0.06
    追
    -0.06
     stalk
    -0.06
    erro
    -0.06
    POSITIVE LOGITS
     Malaysian
    0.06
     تمامی
    0.06
    ；
    0.06
     *****
    0.06
     Routing
    0.06
    ({"
    0.06
     Accessories
    0.06
     Yine
    0.06
    _SS
    0.06
     Vik
    0.06
    Act Density 0.020%

    No Known Activations