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

    Neuronpedia

    INDEX
    Explanations

    =True

    np_max-act · gemini-2.0-flash

    The neuron fires on boolean‐flag settings in code—i.e. occurrences of True or False used as keyword argument values (like unique=True, null=False, primary_key=True, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    mach
    -0.08
     Moj
    -0.07
     Mercer
    -0.07
     enamel
    -0.07
     Eng
    -0.07
    expired
    -0.06
     kanal
    -0.06
     Burg
    -0.06
    Whether
    -0.06
     brutally
    -0.06
    POSITIVE LOGITS
    ||||
    0.07
    ้นท
    0.07
     planetary
    0.06
     <",
    0.06
    .xxx
    0.06
    τερα
    0.06
    ải
    0.06
    ¯Â
    0.06
     indexPath
    0.06
    .IsNullOr
    0.06
    Act Density 0.003%

    No Known Activations