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

    Neuronpedia

    INDEX
    Explanations

    Initials/Names

    np_max-act · gemini-2.0-flash

    This neuron detects capitalized proper nouns, especially names of people and organizations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     allocator
    -0.06
    شتر
    -0.06
    istically
    -0.06
    _val
    -0.06
     Shapiro
    -0.06
    られ
    -0.06
     embodiments
    -0.06
    .optimizer
    -0.06
    서관
    -0.06
     housed
    -0.06
    POSITIVE LOGITS
     sư
    0.08
     �
    0.06
    )m
    0.06
     gymn
    0.06
    .SwingConstants
    0.06
     jednot
    0.06
    infos
    0.06
    เทพ
    0.06
     quilt
    0.06
    (instruction
    0.06
    Act Density 0.090%

    No Known Activations