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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t respond to any token patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    alyzed
    -0.07
    assage
    -0.07
     SCRIPT
    -0.06
    iParam
    -0.06
    =user
    -0.06
    OOM
    -0.06
    following
    -0.06
    =view
    -0.06
    LOOD
    -0.06
    .IsFalse
    -0.06
    POSITIVE LOGITS
    SAFE
    0.06
     dread
    0.06
    Possible
    0.06
     mái
    0.06
     He
    0.06
    .Or
    0.06
     balk
    0.06
     Mỹ
    0.06
    windows
    0.06
    项
    0.05
    Act Density 0.008%

    No Known Activations