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

    Neuronpedia

    INDEX
    Explanations

    Type

    np_max-act · gemini-2.0-flash

    The neuron activates on high-precision decimal numbers (floating-point literals with several digits after the decimal).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     honoring
    -0.07
     ua
    -0.06
    ,",
    -0.06
     delegation
    -0.06
     interpersonal
    -0.06
     cub
    -0.06
    Celebr
    -0.06
    elial
    -0.06
    .Not
    -0.06
     은
    -0.06
    POSITIVE LOGITS
     Melanie
    0.08
    054
    0.07
    value
    0.07
    _Flag
    0.07
     halluc
    0.07
    Type
    0.06
    142
    0.06
    ruptcy
    0.06
     후보
    0.06
    jn
    0.06
    Act Density 0.003%

    No Known Activations