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

    Neuronpedia

    INDEX
    Explanations

    diverse topics

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of the word “system” (and closely related technical terms) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     counterfeit
    -0.07
    AspNet
    -0.06
    rysler
    -0.06
     +'
    -0.06
     flair
    -0.06
    면적
    -0.06
     applic
    -0.06
    elementType
    -0.06
     Ali
    -0.06
    Director
    -0.06
    POSITIVE LOGITS
    SN
    0.07
    주
    0.07
    /U
    0.06
    سال
    0.06
    ér
    0.06
     gbc
    0.06
    sms
    0.06
    (secret
    0.06
    acers
    0.06
    ork
    0.06
    Act Density 0.083%

    No Known Activations