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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.71
    Personensuche
    -0.69
    +#+#
    -0.64
    󠁢
    -0.61
    "]];
    -0.61
     htons
    -0.60
    WebServlet
    -0.60
    DebuggerNonUser
    -0.59
     the
    -0.59
    $}}
    -0.58
    POSITIVE LOGITS
     SUDOC
    0.52
    ,‎
    0.51
     surla
    0.47
    Jîn
    0.46
    ,
    0.46
     then
    0.44
    ὶ
    0.43
    :✨
    0.43
     drum
    0.41
     expect
    0.40
    Act Density 0.004%

    No Known Activations