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

    Neuronpedia

    INDEX
    Explanations

    Months

    np_max-act · gemini-2.0-flash

    The neuron is mainly detecting numeric tokens (e.g. digits, dates, version numbers) in the HTML.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uyen
    -0.07
    .userName
    -0.07
    etat
    -0.07
    ivent
    -0.06
    pressed
    -0.06
     Natal
    -0.06
     Pep
    -0.06
    ucus
    -0.06
     技
    -0.06
    GridLayout
    -0.06
    POSITIVE LOGITS
    /rc
    0.07
     perman
    0.07
     testimonials
    0.07
    Recognition
    0.07
     ¦
    0.07
     kro
    0.07
     privacy
    0.06
     trolls
    0.06
     setDate
    0.06
     transl
    0.06
    Act Density 0.009%

    No Known Activations