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

    Neuronpedia

    INDEX
    Explanations

    switch cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insieme
    0.85
     ogni
    0.77
     другими
    0.76
     innymi
    0.75
     цього
    0.74
     BUT
    0.72
    0.72
     samen
    0.70
     усилия
    0.70
     druge
    0.69
    POSITIVE LOGITS
     case
    2.40
    case
    2.34
    Case
    2.16
     Case
    2.03
     caso
    1.70
     cases
    1.69
    CASE
    1.67
     CASE
    1.67
     случае
    1.65
    ケース
    1.54
    Act Density 0.013%

    No Known Activations