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

    Neuronpedia

    INDEX
    Explanations

    mp

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of specific media file formats (e.g. MP3, MP4, AVI, WAV).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    erton
    -0.07
    atum
    -0.07
    ्तन
    -0.07
     zat
    -0.07
    OTION
    -0.06
     Contractor
    -0.06
     Ellison
    -0.06
    aan
    -0.06
     сест
    -0.06
     вин
    -0.06
    POSITIVE LOGITS
     MP
    0.11
    (mp
    0.10
     mp
    0.09
    _MP
    0.08
    /mp
    0.08
    Mp
    0.08
     Mp
    0.08
    	mp
    0.07
    .mp
    0.07
     DP
    0.07
    Act Density 0.006%

    No Known Activations