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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    łac
    0.46
    吠
    0.45
    М
    0.45
    áreas
    0.44
    ebilir
    0.44
    ભાર
    0.44
    张
    0.44
    錬
    0.43
    eszcze
    0.43
    áže
    0.43
    POSITIVE LOGITS
     hole
    0.45
    abbit
    0.40
     airflow
    0.40
     output
    0.39
     package
    0.39
    (
    0.39
     water
    0.39
     purported
    0.39
     backs
    0.39
     WiFi
    0.38
    Act Density 0.007%

    No Known Activations