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 fires on language expressing technical requirements or desirability (e.g. “necessary,” “desirable,” “would,” “in such a situation,” “it is necessary”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ing
    -0.06
     CES
    -0.06
     bulun
    -0.06
     affiliate
    -0.06
     longitud
    -0.06
     taj
    -0.06
     professions
    -0.06
    decimal
    -0.06
     Jame
    -0.06
    magic
    -0.06
    POSITIVE LOGITS
    :NO
    0.07
     그림
    0.07
    .rstrip
    0.07
     (!_
    0.07
    .rooms
    0.06
    sgi
    0.06
    .UtcNow
    0.06
    .Transform
    0.06
     getArguments
    0.06
    .setAuto
    0.06
    Act Density 0.064%

    No Known Activations