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

    Neuronpedia

    INDEX
    Explanations

    usb

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of “usb” (e.g. in include paths, identifiers, and comments), i.e. it detects the substring “usb.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ков
    -0.07
    ofil
    -0.06
    (tb
    -0.06
     architectural
    -0.06
    /screens
    -0.06
     obs
    -0.06
    subs
    -0.06
    nds
    -0.06
    _notifier
    -0.06
     şek
    -0.06
    POSITIVE LOGITS
     flips
    0.07
     involuntary
    0.06
     unstoppable
    0.06
    ُوا
    0.06
    _Current
    0.06
    /AP
    0.06
     senha
    0.06
    
    0.06
     Fehler
    0.06
    _Zero
    0.06
    Act Density 0.003%

    No Known Activations