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

    Neuronpedia

    INDEX
    Explanations

    data structures and programming concepts

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

    numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ог
    -0.37
    空
    -0.36
    tagPool
    -0.33
    favor
    -0.32
    zur
    -0.32
    󠁢
    -0.32
    장
    -0.30
    ania
    -0.30
    kej
    -0.29
    czyk
    -0.29
    POSITIVE LOGITS
    tvguidetime
    0.73
    存于互联网档案馆
    0.61
     AssemblyCompany
    0.61
    \{\\
    0.56
    rrggbb
    0.52
    Tembelea
    0.52
     Infórmanos
    0.50
    Espèce
    0.50
    twimg
    0.50
    awtextra
    0.49
    Act Density 0.003%

    No Known Activations