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

    Neuronpedia

    INDEX
    Explanations

    character sequences from multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sehr
    0.41
     heures
    0.38
     vous
    0.37
     bạn
    0.37
     avete
    0.36
    \
    0.36
     puede
    0.35
     muito
    0.35
     hebben
    0.35
     esperienze
    0.35
    POSITIVE LOGITS
    ת
    0.42
    ే
    0.34
    ↵↵
    0.33
    תן
    0.32
    ა
    0.31
    ಗಳನ್ನು
    0.28
     plummet
    0.28
    תה
    0.28
    고사
    0.28
    לב
    0.28
    Act Density 16.220%

    No Known Activations