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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     penal
    0.43
     hypers
    0.43
     TestAvg
    0.42
     ConcurrentTask
    0.42
     დაკ
    0.41
    懷
    0.41
     PWMB
    0.40
     書い
    0.39
     Miner
    0.39
     amenity
    0.38
    POSITIVE LOGITS
     také
    0.42
    csak
    0.40
    ことも
    0.40
     होंगे
    0.39
    uka
    0.39
    ല
    0.38
    Sister
    0.38
    presence
    0.38
    agian
    0.38
    ęcia
    0.38
    Act Density 0.000%

    No Known Activations