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

    Neuronpedia

    INDEX
    Explanations

    Chart

    np_max-act · gemini-2.0-flash

    This neuron recognizes the characteristic “How To [Verb] A [Noun] In [Tool]” pattern of tutorial or “how-to” headings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     DOT
    -0.06
    说
    -0.06
     appraisal
    -0.06
     کمتر
    -0.06
     عصر
    -0.06
    >You
    -0.06
     Empire
    -0.05
    명
    -0.05
     Serialize
    -0.05
     přech
    -0.05
    POSITIVE LOGITS
    (byte
    0.07
    ()))↵↵
    0.07
     electrom
    0.06
    기타
    0.06
    _links
    0.06
    ียนร
    0.06
    -parts
    0.06
     winters
    0.06
    '))↵↵
    0.06
    (md
    0.06
    Act Density 0.015%

    No Known Activations