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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -girl
    -0.08
     girls
    -0.07
     electron
    -0.07
    信号
    -0.06
    uel
    -0.06
    lder
    -0.06
     Infantry
    -0.06
    }else
    -0.06
     Handy
    -0.06
     titre
    -0.06
    POSITIVE LOGITS
     (...
    0.07
    庖
    0.07
    (policy
    0.07
    减排
    0.07
     compét
    0.07
    ˋ
    0.07
    奥巴马
    0.07
    _UN
    0.07
    🗽
    0.06
    밈
    0.06
    Act Density 0.034%

    No Known Activations