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

    Neuronpedia

    INDEX
    Explanations

    suits if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    начала
    0.78
     trochę
    0.69
     হয়তো
    0.68
     बीसीसीआई
    0.68
     baan
    0.67
     Begriffe
    0.66
    刚才
    0.66
    ównie
    0.66
     කරන්න
    0.66
    өрд
    0.65
    POSITIVE LOGITS
     under
    3.21
     when
    2.81
     Under
    2.62
    when
    2.59
    under
    2.46
     quando
    2.45
    Under
    2.42
     When
    2.36
     cuando
    2.35
     WHEN
    2.35
    Act Density 0.931%

    No Known Activations