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

    Neuronpedia

    INDEX
    Explanations

    Measurement

    np_max-act · gemini-2.0-flash

    The neuron activates on verbs that describe quantitative experimental measurements or determinations (e.g. “determined,” “measured,” “investigated”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     webpage
    -0.07
    ической
    -0.07
    .Pending
    -0.07
    ecc
    -0.07
     Schwartz
    -0.06
     Words
    -0.06
    、中
    -0.06
     Podle
    -0.06
    کس
    -0.06
     zoning
    -0.06
    POSITIVE LOGITS
    mui
    0.07
    �
    0.06
    <!--<
    0.06
    _logits
    0.06
    으면
    0.06
    审核
    0.06
    _prior
    0.06
    .joda
    0.06
    ことで
    0.06
     노하우
    0.06
    Act Density 0.022%

    No Known Activations