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

    Neuronpedia

    INDEX
    Explanations

    academic/technical language

    np_max-act · gemini-2.0-flash

    The neuron activates on specialized scientific or technical concept words—e.g. names of effects, protocols, schemes, phenomena—that commonly appear in formal research descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     folklore
    -0.07
    Layers
    -0.07
    щие
    -0.06
     monkeys
    -0.06
    �
    -0.06
    .fields
    -0.06
     chữa
    -0.06
    information
    -0.06
     Lv
    -0.06
     справ
    -0.06
    POSITIVE LOGITS
    ContextMenu
    0.06
    ∏
    0.06
    EditingController
    0.06
     companyId
    0.06
    .jasper
    0.06
     mer
    0.06
    ====↵
    0.06
    ！！↵↵
    0.06
    -admin
    0.06
    .changed
    0.06
    Act Density 0.120%

    No Known Activations