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

    Neuronpedia

    INDEX
    Explanations

    Parentheses/brackets

    np_max-act · gemini-2.0-flash

    This neuron detects Markdown formatting tokens—especially link brackets “[” “]” and parentheses “(” “)”, as well as bold markers like “**”.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ologne
    -0.07
     ters
    -0.07
     Тер
    -0.07
    ця
    -0.07
    uploader
    -0.06
    _ix
    -0.06
     laws
    -0.06
    وپ
    -0.06
     Ven
    -0.06
     imprimir
    -0.06
    POSITIVE LOGITS
     cca
    0.06
     getSupportActionBar
    0.06
    breaker
    0.06
     accessor
    0.06
     �
    0.05
     setSupportActionBar
    0.05
    (utf
    0.05
     uint
    0.05
    DECL
    0.05
     sudo
    0.05
    Act Density 0.003%

    No Known Activations