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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron is essentially dead—it never activates on any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Often
    -0.07
     Lynch
    -0.07
     Dent
    -0.06
     Protect
    -0.06
    RELEASE
    -0.06
     Deliver
    -0.06
    Goal
    -0.06
     Bond
    -0.06
     cling
    -0.06
    Crystal
    -0.06
    POSITIVE LOGITS
    APER
    0.07
     Фед
    0.07
    necessary
    0.07
    isko
    0.07
    opia
    0.06
    omo
    0.06
     обще
    0.06
    ійської
    0.06
    ائمة
    0.06
     jsonData
    0.06
    Act Density 0.006%

    No Known Activations