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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    This neuron doesn’t reliably activate on any tokens—essentially it’s inactive and doesn’t detect any feature.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Oops
    -0.07
     lifting
    -0.06
     kittens
    -0.06
    kud
    -0.06
     sup
    -0.06
    fld
    -0.06
     wink
    -0.06
    ifting
    -0.06
    Putting
    -0.06
    ,on
    -0.06
    POSITIVE LOGITS
    emacs
    0.06
    ,status
    0.06
    _ACL
    0.06
    ネル
    0.06
    scopic
    0.06
    ması
    0.06
    .Math
    0.06
    pygame
    0.06
    تش
    0.06
     param
    0.06
    Act Density 0.002%

    No Known Activations