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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ગી
    1.52
    م
    0.99
     دوباره
    0.98
    Ken
    0.98
    G
    0.97
    Take
    0.95
    郢
    0.94
    猬
    0.94
    可能
    0.93
     लिव
    0.93
    POSITIVE LOGITS
    ennzeichnet
    1.38
     те
    1.38
     kanssa
    1.36
     fortunate
    1.34
     sacrificing
    1.33
     percentage
    1.32
     versatility
    1.30
    percentage
    1.27
    秥
    1.26
     caloric
    1.26
    Act Density 0.000%

    No Known Activations