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

    Neuronpedia

    INDEX
    Explanations

    logging and error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    см
    0.41
    说完
    0.41
    ('''
    0.39
    muster
    0.38
    肐
    0.38
    Lor
    0.38
    ("""
    0.38
     만족
    0.38
    rotechn
    0.37
     مرحبا
    0.37
    POSITIVE LOGITS
    [`
    0.40
    找不到
    0.40
     `
    0.39
    ログ
    0.37
     `%
    0.36
    ArchiveAction
    0.35
     celebrity
    0.35
     betreff
    0.35
     tags
    0.35
    allas
    0.34
    Act Density 0.011%

    No Known Activations