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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash

    This neuron detects numeric list markers (e.g. “1.”, “2.”, etc.) that introduce numbered steps or items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rray
    -0.07
    _ORIGIN
    -0.06
     teasing
    -0.06
     therein
    -0.06
     autos
    -0.06
    handler
    -0.06
     teng
    -0.06
    Vehicle
    -0.06
     flotation
    -0.06
    ी-
    -0.06
    POSITIVE LOGITS
    (evt
    0.06
     requisite
    0.06
    柔
    0.06
    ="'.
    0.06
    Disposed
    0.06
    AuthGuard
    0.05
     pozisyon
    0.05
     colorWith
    0.05
    gboolean
    0.05
    ีพ
    0.05
    Act Density 0.212%

    No Known Activations