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

    Neuronpedia

    INDEX
    Explanations

    boolean operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.78
    rungsseite
    -0.75
    IndentedString
    -0.75
    DoubleQuotes
    -0.73
     ujednoznacz
    -0.72
     autorytatywna
    -0.72
    -0.69
    devamını
    -0.67
     يتيمه
    -0.67
    <?
    -0.62
    POSITIVE LOGITS
     unable
    0.84
     failed
    0.81
     inability
    0.76
     cannot
    0.73
     Unable
    0.71
     fails
    0.69
    /
    0.68
     lacks
    0.67
     ineffective
    0.67
     weren
    0.66
    Act Density 0.007%

    No Known Activations