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

    Neuronpedia

    INDEX
    Explanations

    terms related to research and educational purposes

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

    research and developments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bordada
    -0.37
     Burk
    -0.36
    +#+#
    -0.35
     cunning
    -0.32
    Symphony
    -0.31
     Cotter
    -0.31
     budeme
    -0.31
    bard
    -0.30
    SwingConstants
    -0.30
     sava
    -0.30
    POSITIVE LOGITS
    afficheront
    0.64
     سكانية
    0.64
     kaarangay
    0.63
     pleaſure
    0.61
     purpoſe
    0.52
     himo
    0.50
     يتيمه
    0.49
    ագրություններ
    0.48
    ſelves
    0.47
    libft
    0.46
    Act Density 0.105%

    No Known Activations