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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    mathematical or numerical expressions involving calculations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects floating‐point numeric tokens (numbers with decimal fractions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     hc
    -0.07
    .setHorizontalAlignment
    -0.07
     Shuffle
    -0.07
     whipping
    -0.06
    trainer
    -0.06
     coil
    -0.06
     assertNotNull
    -0.06
     rdf
    -0.06
     osob
    -0.06
     sermon
    -0.06
    POSITIVE LOGITS
     Debate
    0.07
    иной
    0.07
    "^
    0.06
    进
    0.06
    ором
    0.06
    rios
    0.06
    े.
    0.06
    _REGEX
    0.06
    ой
    0.06
     Neo
    0.06
    Act Density 0.003%

    No Known Activations