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

    Neuronpedia

    INDEX
    Explanations

    correcting errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    પર
    0.46
     cushions
    0.46
    ხ
    0.45
     opiek
    0.45
     attackers
    0.44
     अटैक
    0.44
     sprawd
    0.44
     daffodils
    0.43
     Regeln
    0.42
     aplatis
    0.42
    POSITIVE LOGITS
     Correct
    0.63
     spelling
    0.61
    Correct
    0.60
    correct
    0.59
    ihe
    0.59
     корре
    0.56
     corre
    0.52
    ives
    0.52
     korrekt
    0.52
    corr
    0.51
    Act Density 0.015%

    No Known Activations