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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ละเอ
    -0.07
     cass
    -0.07
     소
    -0.07
    好
    -0.07
    قصر
    -0.07
    冠
    -0.07
     crochet
    -0.07
    cbd
    -0.07
    �
    -0.07
    .FILL
    -0.06
    POSITIVE LOGITS
     languages
    0.08
     defenders
    0.07
     אלקטרוני
    0.07
    릏
    0.07
     defective
    0.07
     pháp
    0.07
    因而
    0.06
     dams
    0.06
    .Errors
    0.06
     savings
    0.06
    Act Density 0.019%

    No Known Activations