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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on stretches of inline mathematical expressions or formulas.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dfs
    -0.07
    @login
    -0.06
    -loop
    -0.06
     Кар
    -0.06
    ignant
    -0.06
     真
    -0.06
    utches
    -0.06
     repositories
    -0.06
     Going
    -0.06
     mer
    -0.06
    POSITIVE LOGITS
     MERCHANTABILITY
    0.07
     elevation
    0.07
    assertInstanceOf
    0.06
    _ABI
    0.06
     слишком
    0.06
    .bi
    0.06
     turnovers
    0.06
     Dumbledore
    0.06
    .scrollHeight
    0.06
    .apiUrl
    0.06
    Act Density 0.004%

    No Known Activations