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

    Neuronpedia

    INDEX
    Explanations

    text formatted in uppercase or small caps style

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

    words with "caps"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MIDDLEWARE
    -0.37
    i
    -0.33
     Figure
    -0.31
    insel
    -0.29
     éven
    -0.28
    oiseau
    -0.28
    dung
    -0.28
    ')));
    -0.28
    y
    -0.27
    fvar
    -0.27
    POSITIVE LOGITS
     caps
    2.33
     Caps
    2.23
    caps
    2.17
    Caps
    2.06
     CAPS
    1.84
    CAPS
    1.75
     capped
    1.37
    capped
    1.31
     capping
    1.26
    capsulation
    1.23
    Act Density 0.013%

    No Known Activations