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

    Neuronpedia

    INDEX
    Explanations

    Forum instructions

    np_max-act · gemini-2.0-flash

    This neuron detects interface/navigation cues, especially words like “register” and “link” that prompt clicking or signing up.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cur
    -0.07
    saved
    -0.07
    268
    -0.07
     Par
    -0.06
    盗
    -0.06
    _positive
    -0.06
     Braves
    -0.06
    924
    -0.06
    .master
    -0.06
     sick
    -0.06
    POSITIVE LOGITS
    uien
    0.07
     »↵↵
    0.07
     vệ
    0.07
     última
    0.06
     keen
    0.06
    ším
    0.06
     Ln
    0.06
     pounding
    0.06
    \Config
    0.06
     mú
    0.06
    Act Density 0.000%

    No Known Activations