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

    Neuronpedia

    INDEX
    Explanations

    following `What`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ھا
    1.29
    ात
    1.16
     LINKS
    1.15
    iong
    1.14
    borderwidth
    1.13
    regex
    1.12
    Angry
    1.12
    decreasing
    1.12
    हा
    1.11
    ailing
    1.11
    POSITIVE LOGITS
    Ꭸ
    1.29
    ঁচ
    1.23
     měli
    1.17
    ся
    1.16
    гне
    1.16
     llevo
    1.14
     diketahui
    1.14
     hicieron
    1.11
     overhaul
    1.11
    𝐥
    1.09
    Act Density 0.000%

    No Known Activations