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

    Neuronpedia

    INDEX
    Explanations

    Hexadecimal strings

    np_max-act · gemini-2.0-flash

    This neuron spot­lights individual tokens containing hexadecimal digits (especially the letters A–F) in the hex dumps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Particip
    -0.07
     Besch
    -0.06
    ,temp
    -0.06
    丝
    -0.06
    _lbl
    -0.06
     праців
    -0.06
    گاهی
    -0.06
     Cheers
    -0.06
     운영
    -0.06
    imp
    -0.06
    POSITIVE LOGITS
    DIC
    0.07
     quảng
    0.07
    ERE
    0.06
     observational
    0.06
     факти
    0.06
    _LOAD
    0.06
    Δεν
    0.06
    reflection
    0.06
     crowdfunding
    0.06
    ال
    0.06
    Act Density 0.007%

    No Known Activations