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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iosis
    0.36
    iertas
    0.36
     পাবার
    0.36
    小时候
    0.35
    DialogInterface
    0.34
    釗
    0.34
    UpInside
    0.34
    सेप्शन
    0.34
    ajout
    0.33
    ighth
    0.33
    POSITIVE LOGITS
     seventy
    1.78
     sixty
    1.77
     eighty
    1.68
     ۱۵
    1.63
     forty
    1.55
     ۶
    1.54
     ۸
    1.52
     २५
    1.51
     ۷
    1.51
     fifty
    1.50
    Act Density 0.064%

    No Known Activations