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
     İslâm
    -0.07
    IU
    -0.07
     tren
    -0.06
    )['
    -0.06
    نع
    -0.06
    داشت
    -0.06
     آزم
    -0.06
     Blessed
    -0.06
    define
    -0.06
     Vys
    -0.06
    POSITIVE LOGITS
     POST
    0.07
     Town
    0.07
     дот
    0.07
    ευ
    0.06
    cwd
    0.06
     Sup
    0.06
    ัดส
    0.06
    ンズ
    0.06
    微
    0.06
     октября
    0.06
    Act Density 0.011%

    No Known Activations