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

    Neuronpedia

    INDEX
    Explanations

    parties and games

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive (a “dead” neuron), failing to detect or respond to any patterns in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _us
    -0.07
    tabpanel
    -0.06
    eted
    -0.06
    =get
    -0.06
    预览
    -0.06
    aunch
    -0.06
     hv
    -0.06
    ials
    -0.06
    KR
    -0.06
     tm
    -0.06
    POSITIVE LOGITS
     Kır
    0.07
     Bü
    0.07
    раз
    0.07
    樣
    0.07
     đỏ
    0.07
     decl
    0.06
    κει
    0.06
    нивер
    0.06
     Bols
    0.06
    .Inter
    0.06
    Act Density 0.021%

    No Known Activations