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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron is selectively detecting timestamp fields and their numeric values (e.g. “Created: 3.091796875 2.837890625…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     imitation
    -0.07
    angepicker
    -0.06
    ilin
    -0.06
     нев
    -0.06
    奉
    -0.06
     squads
    -0.06
    projection
    -0.06
    _pad
    -0.06
    Distribution
    -0.06
     strains
    -0.06
    POSITIVE LOGITS
    цією
    0.06
    riday
    0.06
    リ
    0.06
     ゝ
    0.06
    )_
    0.06
    swagger
    0.06
    symbol
    0.06
     naughty
    0.06
     COMMENTS
    0.06
     должен
    0.06
    Act Density 0.001%

    No Known Activations