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

    Neuronpedia

    INDEX
    Explanations

    examining content and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perfekt
    0.60
     perfetta
    0.58
     Depending
    0.54
     Tells
    0.53
     perfe
    0.52
     parfaite
    0.52
    Depending
    0.52
     tailoring
    0.51
     可愛い
    0.50
     perfeito
    0.50
    POSITIVE LOGITS
     examining
    0.85
     examination
    0.79
     examine
    0.76
     Examining
    0.75
    exam
    0.72
     Examination
    0.72
    Exam
    0.69
     examin
    0.69
    examine
    0.69
     examined
    0.67
    Act Density 0.060%

    No Known Activations