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

    Neuronpedia

    INDEX
    Explanations

    listing options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     부분을
    0.92
     ಕರಿಬೇವಿನ
    0.89
     subunits
    0.81
     ಕರಿ
    0.80
     කියලා
    0.80
     আফ্রিকার
    0.78
    سری
    0.78
    enters
    0.78
     millioner
    0.77
    .'.
    0.77
    POSITIVE LOGITS
     Ital
    0.69
     sv
    0.68
    स्टिक
    0.67
     Him
    0.66
     endereco
    0.65
     historia
    0.62
     Dams
    0.61
    लेश
    0.61
     Ages
    0.61
     Ev
    0.61
    Act Density 0.045%

    No Known Activations