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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on floating-point numeric tokens (decimal numbers) in the document.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     roi
    -0.07
     préc
    -0.07
    елів
    -0.07
    );}↵↵
    -0.06
     тим
    -0.06
     dzieci
    -0.06
    )})↵
    -0.06
     проти
    -0.06
    leur
    -0.06
     zi
    -0.06
    POSITIVE LOGITS
    riendly
    0.06
    ?<
    0.06
     이유
    0.06
     Product
    0.06
    ConstraintMaker
    0.06
     insn
    0.06
    DownList
    0.06
     submit
    0.06
    ⌒
    0.06
    iente
    0.06
    Act Density 0.005%

    No Known Activations