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

    Neuronpedia

    INDEX
    Explanations

    quantifier + case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    μισ
    -0.87
    的东西
    -0.83
     alphabet
    -0.81
     tensions
    -0.79
    zensionen
    -0.78
     froid
    -0.77
    gten
    -0.77
    Ebay
    -0.76
     短
    -0.74
     spreads
    -0.74
    POSITIVE LOGITS
     cases
    3.80
     case
    2.45
     Cases
    2.44
    cases
    2.41
    Cases
    2.36
     casos
    2.20
     instances
    2.11
     CASES
    1.82
     kasus
    1.72
     경우
    1.66
    Act Density 0.082%

    No Known Activations