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

    Neuronpedia

    INDEX
    Explanations

    long

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tersebut
    -0.07
    SITE
    -0.06
     зб
    -0.06
     přiz
    -0.06
    �
    -0.06
    пор
    -0.06
    .query
    -0.06
     Sporting
    -0.06
    یست
    -0.06
    کرد
    -0.06
    POSITIVE LOGITS
    -int
    0.07
    -employed
    0.07
    イツ
    0.06
    LLU
    0.06
    Pressure
    0.06
    MON
    0.06
    Cd
    0.06
    Look
    0.06
    Perfect
    0.06
    -Language
    0.06
    Act Density 0.003%

    No Known Activations