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

    Neuronpedia

    INDEX
    Explanations

    doesn't/don't

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     препратки
    -0.65
     >=",
    -0.53
    QApplication
    -0.52
     ويكيپيديا
    -0.49
    ylde
    -0.49
    ⤹
    -0.49
    voici
    -0.49
     Familienname
    -0.48
    SuspendLayout
    -0.48
     Care
    -0.47
    POSITIVE LOGITS
     doesn
    1.53
    doesn
    1.20
     don
    1.20
     doesnt
    1.17
     Doesn
    1.15
    Doesn
    1.12
     dosen
    1.11
     dont
    1.00
     does
    0.99
    don
    0.92
    Act Density 0.000%

    No Known Activations