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

    Neuronpedia

    INDEX
    Explanations

    for simplicity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पाँच
    0.46
     హి
    0.46
     जया
    0.43
    JSONArray
    0.43
     ブラ
    0.43
     pertinentes
    0.43
     desgr
    0.42
    Deg
    0.42
     cinque
    0.42
     beaux
    0.42
    POSITIVE LOGITS
    we
    0.54
    the
    0.49
    direct
    0.48
    ir
    0.48
    culoskeletal
    0.47
     we
    0.46
    et
    0.46
    our
    0.46
    myp
    0.45
    ’
    0.45
    Act Density 0.003%

    No Known Activations