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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     handen
    0.36
    verde
    0.36
    ন্দের
    0.34
    atzen
    0.34
     lysosomes
    0.33
    prompt
    0.32
    idane
    0.32
    imentos
    0.31
     ispit
    0.31
    fclose
    0.31
    POSITIVE LOGITS
    k
    0.46
    ای
    0.38
    ه
    0.35
    ك
    0.33
    м
    0.32
    ल
    0.32
    ̶
    0.32
    סה
    0.32
     marshmallow
    0.31
    eresis
    0.31
    Act Density 0.115%

    No Known Activations