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

    Neuronpedia

    INDEX
    Explanations

    distinctness/separation

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of regional linguistic or dialectal variations (e.g., differences in accent or local usage).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     executive
    -0.07
     left
    -0.07
     killers
    -0.07
     imports
    -0.07
     sdk
    -0.07
     sense
    -0.06
     killing
    -0.06
     killed
    -0.06
     Killer
    -0.06
    ע
    -0.06
    POSITIVE LOGITS
    Alpha
    0.07
    ).\
    0.06
    .NonNull
    0.06
     stip
    0.06
    abis
    0.06
    itat
    0.06
     Clinic
    0.06
     PdfP
    0.06
     Magnus
    0.06
    Formatter
    0.06
    Act Density 0.034%

    No Known Activations