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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia

    np_max-act · gemini-2.0-flash

    This neuron never activates on any content—it’s effectively “dead” and doesn’t detect any pattern in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dealership
    -0.07
     dedicate
    -0.07
    Triangles
    -0.06
    DU
    -0.06
    Base
    -0.06
     rip
    -0.06
    -box
    -0.06
    -0.06
    pit
    -0.06
     polygons
    -0.06
    POSITIVE LOGITS
    does
    0.07
    üfus
    0.07
    .auth
    0.06
     Kč
    0.06
    ynı
    0.06
    '[
    0.06
     потріб
    0.06
     нен
    0.06
    _tid
    0.06
     діяль
    0.06
    Act Density 0.009%

    No Known Activations