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

    Neuronpedia

    INDEX
    Explanations

    i've always been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yourselves
    0.82
    されました
    0.77
    চ্ছেন
    0.73
    のでしょう
    0.72
     دارید
    0.72
    お願いします
    0.71
     показали
    0.70
     등으로
    0.70
     themselves
    0.70
    ませんか
    0.69
    POSITIVE LOGITS
     myself
    1.25
     personally
    1.21
     heard
    1.17
     personalmente
    1.14
     never
    1.13
     noticed
    1.04
     my
    1.02
     rarely
    1.02
     hear
    1.01
     NEVER
    0.98
    Act Density 0.017%

    No Known Activations