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

    Neuronpedia

    INDEX
    Explanations

    creation and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دارد
    0.37
    idać
    0.36
     niego
    0.35
    nimmt
    0.33
     aveva
    0.33
    appears
    0.32
    য়েছে
    0.32
     hanno
    0.32
    sembles
    0.32
     می‌دهد
    0.32
    POSITIVE LOGITS
    与
    0.34
    ↵
    0.34
    การ
    0.34
    の
    0.33
    活動
    0.32
    /
    0.31
    お
    0.31
    における
    0.31
     де
    0.31
    自己的
    0.30
    Act Density 0.078%

    No Known Activations