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

    Neuronpedia

    INDEX
    Explanations

    short answer is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ঞ্ছ
    0.70
     proceeds
    0.70
     כמ
    0.69
     approached
    0.68
    entionally
    0.67
     realizing
    0.66
     imply
    0.66
     requests
    0.66
     recognizing
    0.65
     happen
    0.65
    POSITIVE LOGITS
    answer
    0.83
    Short
    0.73
     kurze
    0.72
     answer
    0.71
    Summary
    0.70
    Answer
    0.68
     kısa
    0.67
     unequivocal
    0.66
    Télé
    0.66
    …?
    0.65
    Act Density 0.120%

    No Known Activations