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

    Neuronpedia

    INDEX
    Explanations

    best foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    汙
    0.41
    claimed
    0.37
    attachment
    0.37
     MBE
    0.37
     beforeDir
    0.37
    expression
    0.36
     circulating
    0.36
    য়ান
    0.36
    污
    0.36
    福建
    0.36
    POSITIVE LOGITS
     melhor
    0.41
     лучший
    0.41
     intruder
    0.40
    Hod
    0.39
     mejor
    0.38
     καλύτε
    0.38
     بهتر
    0.38
     лучше
    0.37
    更好的
    0.37
    odus
    0.37
    Act Density 0.000%

    No Known Activations