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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Klo
    -0.07
     precious
    -0.07
     studied
    -0.07
    ЙЙ
    -0.07
     scope
    -0.06
    发现
    -0.06
     Goose
    -0.06
     để
    -0.06
    伯
    -0.06
    APP
    -0.06
    POSITIVE LOGITS
    0.07
    executable
    0.06
    橋
    0.06
    箱
    0.06
    кид
    0.06
    ёт
    0.06
    谋
    0.06
     imitation
    0.06
    andr
    0.05
    lanmış
    0.05
    Act Density 0.023%

    No Known Activations