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

    Neuronpedia

    INDEX
    Explanations

    age and content ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     성공
    -0.75
     intimidate
    -0.69
    犒
    -0.68
    mployment
    -0.68
     col
    -0.68
     относится
    -0.67
    invalidate
    -0.65
     univariate
    -0.65
    fru
    -0.65
     luz
    -0.65
    POSITIVE LOGITS
     parental
    2.14
    parental
    1.81
     Parental
    1.72
     age
    1.72
     rating
    1.58
     ratings
    1.54
    Parental
    1.52
     Age
    1.51
     parents
    1.43
    Age
    1.43
    Act Density 0.020%

    No Known Activations