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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions and alternatives

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

    or and equivalents in other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.52
     Inſ
    -0.43
    EVERY
    -0.43
     jūs
    -0.42
     juſ
    -0.41
    OGND
    -0.40
    hånd
    -0.40
    everything
    -0.40
     viņ
    -0.40
    visuel
    -0.39
    POSITIVE LOGITS
     or
    1.13
     hoặc
    1.04
     또는
    0.97
     vagy
    0.96
     или
    0.95
    或
    0.93
     或
    0.92
    或者
    0.91
    または
    0.90
     eller
    0.90
    Act Density 0.047%

    No Known Activations