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

    Neuronpedia

    INDEX
    Explanations

    titles or phrases referring to artistic or literary works

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

    common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.79
     Taktlose
    -0.71
     Infórmanos
    -0.66
    httphttps
    -0.64
    DockStyle
    -0.62
     Signalez
    -0.59
    Хьажоргаш
    -0.56
    afficheront
    -0.53
    DoubleQuotes
    -0.53
    期刊论文
    -0.51
    POSITIVE LOGITS
    Transport
    0.39
    apimachinery
    0.38
    Film
    0.38
    Runtime
    0.38
    Touch
    0.37
     verdi
    0.37
    Drug
    0.36
    Race
    0.36
    Handling
    0.36
     inversión
    0.36
    Act Density 0.147%

    No Known Activations