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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     predecessors
    -0.07
    降低成本
    -0.07
     ransom
    -0.07
     faces
    -0.07
     backstage
    -0.07
    引爆
    -0.07
    asha
    -0.06
     actionable
    -0.06
    🤷
    -0.06
     interruption
    -0.06
    POSITIVE LOGITS
    систем
    0.07
    كا
    0.07
    凡本网
    0.06
    网讯
    0.06
     technique
    0.06
    ／
    0.06
    ➦
    0.06
    ể
    0.06
     dés
    0.06
    �
    0.06
    Act Density 0.002%

    No Known Activations