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

    Neuronpedia

    INDEX
    Explanations

    origin meant, hotel industry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interestingly
    0.40
    驄
    0.39
     নিষ্ঠুর
    0.39
    бат
    0.38
     cứu
    0.38
    救
    0.38
     যেই
    0.37
    ilded
    0.36
    輙
    0.36
    之下
    0.36
    POSITIVE LOGITS
     pas
    0.45
     psal
    0.41
     bene
    0.39
    ాలా
    0.38
     upstream
    0.38
    styl
    0.38
     operator
    0.38
     Joel
    0.37
     stylus
    0.37
     stylistic
    0.36
    Act Density 0.000%

    No Known Activations