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

    Neuronpedia

    INDEX
    Explanations

    sentence fragments

    np_max-act · gemini-2.0-flash

    The neuron detects phrases that refer to “us” framed by quantifiers—e.g. “both of us,” “one of us”—highlighting mentions of the speaker and another.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    [];
↵
    -0.06
    angstrom
    -0.06
    .ctrl
    -0.06
    -space
    -0.06
    від
    -0.06
     secure
    -0.06
     mirrors
    -0.06
     Ling
    -0.06
    _MAXIMUM
    -0.06
    amura
    -0.06
    POSITIVE LOGITS
     말했다
    0.07
     такие
    0.06
    ใบ
    0.06
     getCategory
    0.06
    изнес
    0.06
    URLRequest
    0.06
     hemp
    0.06
     vaping
    0.06
     af
    0.06
    gression
    0.06
    Act Density 0.123%

    No Known Activations