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

    Neuronpedia

    INDEX
    Explanations

    the word "where."

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

    where it is or happens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.46
    EndContext
    -0.40
     createState
    -0.40
    calf
    -0.40
     khong
    -0.39
    colazione
    -0.39
     Xp
    -0.39
     Nec
    -0.37
    ńcz
    -0.37
    }{*}{
    -0.37
    POSITIVE LOGITS
     autorytatywna
    0.58
     resourceCulture
    0.58
    errHandler
    0.57
     fédé
    0.53
     Inscrivez
    0.52
     purpoſe
    0.51
     pouvoit
    0.50
     <=",
    0.50
    LookAnd
    0.49
     plufieurs
    0.49
    Act Density 0.002%

    No Known Activations