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

    Neuronpedia

    INDEX
    Explanations

    NOT

    np_max-act · gemini-2.0-flash

    The neuron detects the phrase “DO NOT” in license or copyright header comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    921
    -0.08
    _mpi
    -0.07
     врем
    -0.06
    .loadData
    -0.06
     ])->
    -0.06
     başvuru
    -0.06
    $
↵
    -0.06
    OfType
    -0.06
     미
    -0.06
    .server
    -0.06
    POSITIVE LOGITS
     booking
    0.08
    sig
    0.07
    ournaments
    0.07
     discrepancies
    0.07
    yalty
    0.07
    Favorites
    0.07
     euth
    0.07
     Colomb
    0.07
     boobs
    0.06
    amily
    0.06
    Act Density 0.002%

    No Known Activations