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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ++;
    0.46
    м
    0.45
    StartZ
    0.45
    数学
    0.45
    عهد
    0.45
    قيق
    0.44
    孱
    0.44
     Configure
    0.44
    ారు
    0.44
     sekolah
    0.43
    POSITIVE LOGITS
     an
    0.51
    ↵↵↵
    0.48
     judi
    0.46
     요
    0.45
     obstruction
    0.45
    uno
    0.44
    ira
    0.43
     dangerously
    0.43
     grossly
    0.43
     icy
    0.43
    Act Density 0.002%

    No Known Activations