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

    Neuronpedia

    INDEX
    Explanations

    references to small or miniature objects

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

    small size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.41
     linho
    -0.39
    wcs
    -0.39
    impianto
    -0.38
     Sill
    -0.38
    addFlags
    -0.37
    calça
    -0.37
    attendre
    -0.36
    Hacker
    -0.36
     "{{
    -0.36
    POSITIVE LOGITS
     tiny
    0.91
     small
    0.86
     miniature
    0.84
    small
    0.81
    miniature
    0.79
     pequeño
    0.77
     SMALL
    0.74
    Small
    0.74
    Smaller
    0.72
     diminutive
    0.72
    Act Density 0.039%

    No Known Activations