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

    Neuronpedia

    INDEX
    Explanations

    trend

    np_max-act · gemini-2.0-flash

    The neuron never fires on any tokens—it doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     submits
    -0.07
    ARRAY
    -0.06
    Hub
    -0.06
    เขต
    -0.06
    >↵↵
    -0.06
    よね
    -0.06
    Hol
    -0.06
    '];?>↵
    -0.06
    allele
    -0.06
    ervlet
    -0.06
    POSITIVE LOGITS
     STRICT
    0.07
     future
    0.06
     realidad
    0.06
     เข
    0.06
     دم
    0.06
    0.06
    атегор
    0.06
     mechanism
    0.06
     INTERN
    0.06
    ческое
    0.06
    Act Density 0.001%

    No Known Activations