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

    Neuronpedia

    INDEX
    Explanations

    Suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     photolibrary
    -0.94
     ſeveral
    -0.84
     itſelf
    -0.83
     AppColors
    -0.83
     ſy
    -0.82
    ^(@)
    -0.81
     Squal
    -0.79
     Monfieur
    -0.79
     myſelf
    -0.78
     $_"
    -0.77
    POSITIVE LOGITS
    ↵↵
    0.62
    ↵
    0.60
    RegressionTest
    0.58
     //
    0.49
    nya
    0.47
    <eos>
    0.46
    </blockquote>
    0.46
    on
    0.46
     change
    0.46
     '
    0.45
    Act Density 0.185%

    No Known Activations