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

    Neuronpedia

    INDEX
    Explanations

    means and averages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.86
    protoimpl
    -0.84
     typelib
    -0.83
     Taktlose
    -0.80
    EndInit
    -0.80
    EndGlobalSection
    -0.79
    :✨
    -0.77
    PerformLayout
    -0.77
    WireFormatLite
    -0.77
    HasForeignKey
    -0.76
    POSITIVE LOGITS
     means
    0.72
     ari
    0.67
     av
    0.67
     geometric
    0.61
     an
    0.59
     arithmetic
    0.57
     avere
    0.54
    几何
    0.54
     ave
    0.54
     arit
    0.49
    Act Density 0.007%

    No Known Activations