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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “hook” (and its variants like “hooking” or “hooks”) in code, marking places where functions or system calls are being intercepted or hooked.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     brigade
    -0.07
     podium
    -0.07
    876
    -0.07
     Harlem
    -0.07
    .toByteArray
    -0.07
    "},
    -0.06
    .RUN
    -0.06
    -document
    -0.06
     obligation
    -0.06
     önlem
    -0.06
    POSITIVE LOGITS
     firmware
    0.07
    alyzer
    0.07
    ste
    0.06
    orgeous
    0.06
     Hao
    0.06
     самостоятель
    0.06
    ертв
    0.06
    =?";↵
    0.06
     SHA
    0.06
    načení
    0.06
    Act Density 0.050%

    No Known Activations