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

    Neuronpedia

    INDEX
    Explanations

    colons/quotes

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric literal tokens—especially decimal‐fraction numbers—wherever they appear.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     군
    -0.07
     repetition
    -0.07
    licence
    -0.07
    سته
    -0.06
     Level
    -0.06
    یزات
    -0.06
    INI
    -0.06
    amel
    -0.06
    Sou
    -0.06
    ansion
    -0.06
    POSITIVE LOGITS
    .AddListener
    0.07
    @@
    0.07
    =True
    0.06
    席
    0.06
     Đài
    0.06
    _CAM
    0.06
     즐
    0.06
    _calendar
    0.06
    �
    0.06
    lacağ
    0.06
    Act Density 0.042%

    No Known Activations