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

    Neuronpedia

    INDEX
    Explanations

    i can spot common

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infl
    0.46
     kappa
    0.46
     inver
    0.46
     inflate
    0.45
    čna
    0.41
    之後
    0.41
     Yahoo
    0.40
     atti
    0.40
    ल्यावर
    0.40
     čega
    0.40
    POSITIVE LOGITS
    小组
    0.43
    暂停
    0.42
    .”)
    0.42
    非常的
    0.42
    Diện
    0.41
    纤
    0.41
    没有任何
    0.41
     करेगी
    0.41
    正确的
    0.41
    毕竟
    0.39
    Act Density 0.011%

    No Known Activations