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

    Neuronpedia

    INDEX
    Explanations

    itself or themselves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yourself
    0.77
    ,
    0.73
     seorang
    0.71
     Andalusia
    0.69
     consultez
    0.65
     '
    0.64
     unforgettable
    0.63
     pensée
    0.62
     jasmine
    0.62
     Mindfulness
    0.62
    POSITIVE LOGITS
     своїх
    1.19
     swoich
    1.16
     своих
    1.15
     свои
    1.12
     svoje
    1.12
     themselves
    1.09
     తమ
    1.07
     தங்கள்
    1.04
     svojih
    1.02
     ತಮ್ಮ
    1.02
    Act Density 0.004%

    No Known Activations