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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron detects language referring to planned future events or upcoming changes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    íd
    -0.06
    urons
    -0.06
     dudes
    -0.06
     devised
    -0.06
     cycling
    -0.06
    osal
    -0.06
     values
    -0.06
    press
    -0.06
     esto
    -0.06
     Revolution
    -0.06
    POSITIVE LOGITS
    (criteria
    0.07
     CONF
    0.07
     зрозум
    0.06
    Col
    0.06
    .=
    0.06
    いに
    0.06
    :.
    0.06
     -,
    0.06
    (entries
    0.06
     ออนไลน
    0.06
    Act Density 0.121%

    No Known Activations