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

    Neuronpedia

    INDEX
    Explanations

    scales and ratings

    np_max-act · gemini-2.0-flash

    This neuron detects prompts asking for a rating on a numeric scale (e.g. “On a scale of 1 to 6…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sorted
    -0.08
    Editors
    -0.07
     tabPage
    -0.07
    count
    -0.06
     judicial
    -0.06
    دیگر
    -0.06
     Bag
    -0.06
     duplicates
    -0.06
     collaborators
    -0.06
    olec
    -0.06
    POSITIVE LOGITS
    .at
    0.07
     rookie
    0.06
     vídeo
    0.06
    就在
    0.06
    월까지
    0.06
    dığı
    0.06
    ::|
    0.06
    mercial
    0.06
     zh
    0.06
    Ệ
    0.06
    Act Density 0.007%

    No Known Activations