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

    Neuronpedia

    INDEX
    Explanations

    code/unusual formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.51
     noDo
    -0.51
    AddField
    -0.46
    ubel
    -0.45
    তথ্যসূত্র
    -0.44
    τας
    -0.43
    baldi
    -0.42
    malen
    -0.42
    ",
    -0.41
    beri
    -0.41
    POSITIVE LOGITS
     purpoſe
    0.83
    ſelf
    0.78
    0.70
    +#+#
    0.70
     pleaſure
    0.69
     myſelf
    0.68
     leaſt
    0.68
     Majefty
    0.67
    verwijspagina
    0.65
     Efq
    0.63
    Act Density 0.087%

    No Known Activations