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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ثلاث
    -0.07
    ▋
    -0.06
     klíč
    -0.06
     تحقیق
    -0.06
     ألف
    -0.06
    iyas
    -0.06
    _middle
    -0.06
     ян
    -0.06
    ̉
    -0.06
     Rek
    -0.06
    POSITIVE LOGITS
     formulated
    0.07
     nhau
    0.07
     ethernet
    0.06
    (Json
    0.06
    .close
    0.06
     percentages
    0.06
     друж
    0.06
    .....↵↵
    0.06
    ----------------
    0.06
    inv
    0.06
    Act Density 0.046%

    No Known Activations