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

    Neuronpedia

    INDEX
    Explanations

    explaining question image game problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ግራም
    0.41
    oC
    0.40
    o
    0.38
    ού
    0.37
     termed
    0.37
    ೩
    0.37
     نیٹ
    0.36
    ುದು
    0.36
    ⤵
    0.35
    da
    0.35
    POSITIVE LOGITS
     for
    0.49
    ायला
    0.48
     для
    0.47
     উপহার
    0.47
     enough
    0.47
     pentru
    0.47
     untuk
    0.46
    для
    0.45
     साबित
    0.44
    有很多
    0.44
    Act Density 0.196%

    No Known Activations