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

    Neuronpedia

    INDEX
    Explanations

    pre- and post- prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    г
    0.38
    m
    0.32
    g
    0.31
    category
    0.31
    െന്ന്
    0.30
    r
    0.29
    а
    0.29
    j
    0.29
    üğünüz
    0.28
    list
    0.28
    POSITIVE LOGITS
     Post
    0.36
    Post
    0.34
     post
    0.33
     ส
    0.33
     freestyle
    0.30
     fouls
    0.30
    โพ
    0.30
     breakouts
    0.30
     En
    0.29
    mortem
    0.28
    Act Density 0.008%

    No Known Activations