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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals or organizations

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

    Names of people and organizations

    np_acts-logits-general · gemini-2.0-flash

    names followed by surnames or verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.97
     autorytatywna
    -0.97
     Taktlose
    -0.86
    Хьажоргаш
    -0.77
    verwijspagina
    -0.77
    хьтан
    -0.76
    oa̍t
    -0.74
     Infórmanos
    -0.74
     ſind
    -0.74
     queſta
    -0.73
    POSITIVE LOGITS
     is
    0.46
    is
    0.40
    1
    0.38
    2
    0.37
     was
    0.35
    The
    0.35
     has
    0.34
    -
    0.33
    是
    0.33
    ans
    0.33
    Act Density 0.307%

    No Known Activations