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

    Neuronpedia

    INDEX
    Explanations

    computer code execution

    np_max-act · gemini-2.0-flash

    This neuron never activates on any input (i.e. it’s effectively “dead”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Davies
    -0.06
     dicho
    -0.06
     adidas
    -0.06
     Das
    -0.06
     dir
    -0.06
    _INPUT
    -0.06
     Lydia
    -0.06
    RSS
    -0.06
    ्वत
    -0.06
    .?
    -0.06
    POSITIVE LOGITS
     посад
    0.07
    感
    0.06
     />}↵
    0.06
     khó
    0.06
     trim
    0.06
    '><
    0.06
    璃
    0.06
     необ
    0.06
     slate
    0.06
     použit
    0.06
    Act Density 0.011%

    No Known Activations