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

    Neuronpedia

    INDEX
    Explanations

    student IDs and usernames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    銀行
    0.80
     fabricate
    0.76
    யமாக
    0.76
     イベント
    0.74
    পাতের
    0.74
    呥
    0.73
    鈕
    0.73
    yesters
    0.73
     berada
    0.73
     partenaires
    0.72
    POSITIVE LOGITS
     scholar
    1.72
     Scholar
    1.65
    Pup
    1.59
     pupil
    1.59
     Pupil
    1.52
     scholars
    1.51
    pup
    1.48
     Lear
    1.44
     Pupils
    1.42
     уче
    1.40
    Act Density 0.017%

    No Known Activations