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

    Neuronpedia

    INDEX
    Explanations

    hacking

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of hacking or computer‐intrusion activities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    çak
    -0.07
    gı
    -0.07
    dum
    -0.07
    |
↵
    -0.07
    imiento
    -0.07
    matchCondition
    -0.06
    uala
    -0.06
    "crypto
    -0.06
    جا
    -0.06
    (clock
    -0.06
    POSITIVE LOGITS
     ability
    0.07
     comunic
    0.07
    领域
    0.06
     residing
    0.06
     Remix
    0.06
     consequential
    0.06
    Listening
    0.06
     Assess
    0.06
     hacking
    0.06
     brushing
    0.06
    Act Density 0.022%

    No Known Activations