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

    Neuronpedia

    INDEX
    Explanations

    customer service complaints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clar
    -0.07
     objetos
    -0.07
    面条
    -0.07
    也不例外
    -0.07
     kl
    -0.07
     inviting
    -0.06
     đảo
    -0.06
    Tar
    -0.06
    梅花
    -0.06
    ameda
    -0.06
    POSITIVE LOGITS
     psychologists
    0.08
    흫
    0.08
    encryption
    0.07
     Corps
    0.07
     HOLD
    0.07
    🚴
    0.07
    מוש
    0.07
     Hacker
    0.06
    ographers
    0.06
     ')
↵
    0.06
    Act Density 0.058%

    No Known Activations