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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Collection
    -0.07
     собі
    -0.06
     Cl
    -0.06
     NAN
    -0.06
     lá
    -0.06
     preventive
    -0.06
    맥
    -0.06
    될
    -0.06
    ")}
    -0.06
     OS
    -0.06
    POSITIVE LOGITS
    ADMIN
    0.07
    του
    0.06
    Immediately
    0.06
    aphore
    0.06
    在线阅读
    0.06
    #plt
    0.06
    ¶¶
    0.06
     Sosyal
    0.06
     franchises
    0.06
     purported
    0.06
    Act Density 0.018%

    No Known Activations