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

    Neuronpedia

    INDEX
    Explanations

    according

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stay
    -0.07
    "
    -0.07
     oste
    -0.06
    ste
    -0.06
     шту
    -0.06
    ”
    -0.06
     Jessica
    -0.06
    �
    -0.06
    jà
    -0.06
    t
    -0.06
    POSITIVE LOGITS
     according
    0.09
     According
    0.09
    ukarı
    0.08
    (in
    0.07
     calc
    0.07
    (Address
    0.07
     पर
    0.07
    ันออก
    0.07
    きな
    0.07
    };
↵
↵
    0.07
    Act Density 0.024%

    No Known Activations