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

    Neuronpedia

    INDEX
    Explanations

    message

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     يست
    -0.07
    ایی
    -0.07
    uesto
    -0.06
    リス
    -0.06
    DDD
    -0.06
    됩니다
    -0.06
     Erotische
    -0.06
    府
    -0.06
    _GenericClass
    -0.06
    iams
    -0.06
    POSITIVE LOGITS
     �
    0.07
     eslint
    0.07
     />)↵
    0.07
     upfront
    0.06
     civic
    0.06
    вав
    0.06
     základní
    0.06
     compliments
    0.06
     boast
    0.06
     Tribal
    0.06
    Act Density 0.021%

    No Known Activations