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

    Neuronpedia

    INDEX
    Explanations

    references to entities involved in partnerships, collaborations, or comparisons

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

    two or both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     réparer
    -0.44
     Süß
    -0.43
     Handel
    -0.43
     elétrica
    -0.43
    SBATCH
    -0.41
     résister
    -0.40
     Chaldean
    -0.40
     Económica
    -0.40
     consulter
    -0.40
     MenuView
    -0.40
    POSITIVE LOGITS
     Beide
    0.65
     Ambos
    0.64
     оба
    0.59
    Both
    0.58
     berdua
    0.55
    Ambos
    0.54
    !*\
    0.54
     beider
    0.54
     beide
    0.53
    -------
    0.53
    Act Density 0.057%

    No Known Activations