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

    Neuronpedia

    INDEX
    Explanations

    directory

    np_max-act · gemini-2.0-flash

    This neuron does not activate on any tokens—it does not detect or respond to any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Archived
    -0.06
    Filed
    -0.06
    amus
    -0.06
    iful
    -0.06
    _months
    -0.06
    unicorn
    -0.06
     dân
    -0.06
    TER
    -0.06
     brides
    -0.06
    Ë
    -0.06
    POSITIVE LOGITS
     Environment
    0.06
     Chain
    0.06
    481
    0.06
    Driver
    0.06
     Factory
    0.06
     Reader
    0.06
    结构
    0.06
     broadcaster
    0.06
    cwd
    0.06
     dann
    0.06
    Act Density 0.004%

    No Known Activations