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

    Neuronpedia

    INDEX
    Explanations

    Select

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “.js” file references in HTML (i.e. JavaScript source filenames).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     synonyms
    -0.07
     antibody
    -0.07
     Token
    -0.07
    Padding
    -0.06
     Raid
    -0.06
    уючи
    -0.06
    BaseContext
    -0.06
     Oxford
    -0.06
     Method
    -0.06
     Question
    -0.06
    POSITIVE LOGITS
    ('=
    0.06
     impunity
    0.06
     ensued
    0.06
     allowNull
    0.06
     раст
    0.06
    프로
    0.06
     eminent
    0.06
    ().'
    0.06
    _pal
    0.06
     mø
    0.06
    Act Density 0.001%

    No Known Activations