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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.44
    UrlResolution
    -0.39
    UserScript
    -0.38
    delwed
    -0.38
    latego
    -0.38
    EDEFAULT
    -0.37
    //</
    -0.37
     onOptions
    -0.36
     AssemblyProduct
    -0.36
    SBATCH
    -0.35
    POSITIVE LOGITS
    Alignment
    1.16
     Alignment
    0.89
     alignment
    0.79
    alignment
    0.71
     alignments
    0.69
     مشين
    0.65
    ografija
    0.59
     aligning
    0.52
     Align
    0.51
     ALIGN
    0.51
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.