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

    Neuronpedia

    INDEX
    Explanations

    bul

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “istanbul” (e.g. in package names, commands, or module requires), i.e. references to the Istanbul code-coverage tool.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rumor
    -0.07
     uintptr
    -0.06
     daha
    -0.06
     Comey
    -0.06
     rady
    -0.06
     lectures
    -0.06
    .EVENT
    -0.06
     quyền
    -0.06
    ':''
    -0.06
    =user
    -0.06
    POSITIVE LOGITS
    _inds
    0.07
    劳
    0.06
    Johnny
    0.06
    Junior
    0.06
     Semester
    0.06
    少年
    0.06
    �
    0.06
     지
    0.06
     overhe
    0.06
     contained
    0.06
    Act Density 0.000%

    No Known Activations