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

    Neuronpedia

    INDEX
    Explanations

    Quantifiers

    np_max-act · gemini-2.0-flash

    This neuron responds to the hyphenated “-time” suffix (as in “full-time”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fuzzy
    -0.07
    505
    -0.07
    variably
    -0.06
    測
    -0.06
    belie
    -0.06
    mh
    -0.06
    according
    -0.06
    ेस
    -0.06
    western
    -0.06
    .Height
    -0.06
    POSITIVE LOGITS
     精
    0.07
     правила
    0.07
    .CG
    0.06
    _DONE
    0.06
     kosten
    0.06
    .permission
    0.06
    (evt
    0.06
     disadv
    0.06
     RAF
    0.06
    ANTA
    0.06
    Act Density 0.157%

    No Known Activations