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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    дання
    -0.08
    roku
    -0.08
     ಬು
    -0.08
    ross
    -0.07
    �
    -0.07
    Mond
    -0.07
    wipe
    -0.07
    跌
    -0.07
    ��
    -0.07
     ві
    -0.07
    POSITIVE LOGITS
    large
    0.12
     large
    0.11
    .large
    0.11
     बड़ी
    0.11
     பெரிய
    0.11
     મોટી
    0.10
     larger
    0.10
     grandes
    0.10
     الكبيرة
    0.10
     పెద్ద
    0.10
    Act Density 0.007%

    No Known Activations