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

    Neuronpedia

    INDEX
    Explanations

    support

    np_max-act · gemini-2.0-flash

    This neuron rarely (if ever) activates—it does not have any identifiable pattern it’s detecting.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     recogn
    -0.07
    .Init
    -0.07
    рь
    -0.07
    ذار
    -0.07
    atform
    -0.06
    别
    -0.06
    ertest
    -0.06
    Probe
    -0.06
     Европ
    -0.06
    .Listen
    -0.06
    POSITIVE LOGITS
     slopes
    0.07
     Stones
    0.07
     loadImage
    0.06
    mere
    0.06
    ();?>
    0.06
     Weg
    0.06
    ….
    0.06
     Türkçe
    0.06
     vyd
    0.06
    mens
    0.06
    Act Density 0.015%

    No Known Activations