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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash

    This neuron detects document metadata lines—specifically source citations and update timestamps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     RW
    -0.08
     hypo
    -0.07
     cola
    -0.07
     eater
    -0.07
    ffmpeg
    -0.06
     Milf
    -0.06
     DropDownList
    -0.06
    _neg
    -0.06
    uitka
    -0.06
    (wrapper
    -0.06
    POSITIVE LOGITS
    孩子
    0.06
     tüm
    0.06
    得到
    0.06
    сыл
    0.06
     transition
    0.06
    猫
    0.06
    ato
    0.06
    하는
    0.06
    原
    0.06
    -inch
    0.06
    Act Density 0.000%

    No Known Activations