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

    Neuronpedia

    INDEX
    Explanations

    compound interest formula

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     روحانی
    0.51
    jük
    0.45
     ها
    0.43
     вза
    0.42
    idin
    0.42
    yl
    0.42
    ки
    0.41
     intimacy
    0.41
     unpopular
    0.40
     Христос
    0.40
    POSITIVE LOGITS
    CHEN
    0.48
    蒇
    0.48
    Polynomial
    0.45
    🎍
    0.44
    爆炸
    0.44
     havde
    0.42
    ፕ
    0.42
    CIA
    0.41
     danni
    0.41
     colect
    0.41
    Act Density 0.002%

    No Known Activations