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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legibility and readability of text

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

    difficulty determining precisely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.71
    DockStyle
    -0.70
    ReusableCell
    -0.68
     estekak
    -0.66
     <<<<<<<<<<<<<<
    -0.65
    RenderAtEndOf
    -0.64
    EDEFAULT
    -0.63
     Biôgrafia
    -0.63
    -0.62
    Хьажоргаш
    -0.61
    POSITIVE LOGITS
    nible
    0.33
     obscured
    0.33
    inaudible
    0.32
    pick
    0.30
    readValue
    0.29
    tät
    0.29
    ╭
    0.28
     pick
    0.28
     mumbled
    0.27
     unintelligible
    0.27
    Act Density 0.042%

    No Known Activations