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

    Neuronpedia

    INDEX
    Explanations

    degree and comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الثانية
    0.43
    ")}
    0.41
     новые
    0.40
    rine
    0.40
     పూ
    0.40
     seconde
    0.39
     новый
    0.39
     после
    0.38
     বলিলাম
    0.38
     Dois
    0.38
    POSITIVE LOGITS
    もっと
    0.85
     more
    0.74
     much
    0.74
     훨씬
    0.74
    更大的
    0.70
     гораздо
    0.69
    更大
    0.66
     elsewhere
    0.66
    훨
    0.64
     bigger
    0.63
    Act Density 0.107%

    No Known Activations