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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tokenizer
    -0.07
     concept
    -0.07
    汨
    -0.07
    人参
    -0.07
    �
    -0.07
     Almighty
    -0.07
    arsi
    -0.07
     bearer
    -0.07
    관광
    -0.07
    清澈
    -0.06
    POSITIVE LOGITS
    좍
    0.07
    ():↵
    0.06
    账
    0.06
    -la
    0.06
    でき
    0.06
    ималь
    0.06
    !"↵
    0.06
    /
↵
    0.06
     موجود
    0.06
    ケー
    0.06
    Act Density 0.002%

    No Known Activations