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

    Neuronpedia

    INDEX
    Explanations

    details related to consumer products and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows conjunctions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    phrases after periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Demikian
    -0.82
     ErrIntOverflow
    -0.82
    TestBed
    -0.81
     >=",
    -0.76
    ]--;
    -0.76
    spesies
    -0.75
     المعيارى
    -0.74
     hence
    -0.72
    InstanceState
    -0.70
     cdti
    -0.69
    POSITIVE LOGITS
     Enjoy
    0.65
    Hurry
    0.64
    Get
    0.64
     Don
    0.63
    And
    0.62
     Get
    0.61
    Don
    0.60
     enjoy
    0.60
     And
    0.60
    Choose
    0.59
    Act Density 0.167%

    No Known Activations