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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foram
    -0.06
     dado
    -0.06
    求购
    -0.06
     було
    -0.06
     мн
    -0.06
     cakes
    -0.06
    -0.06
     sushi
    -0.06
    θο
    -0.06
     생성
    -0.06
    POSITIVE LOGITS
    ATAR
    0.07
    ampus
    0.06
     lazım
    0.06
    contest
    0.06
    insic
    0.06
    /lab
    0.06
     effortless
    0.06
     ^
    0.06
     کان
    0.06
    ��이
    0.06
    Act Density 0.015%

    No Known Activations