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

    Neuronpedia

    INDEX
    Explanations

    word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     og
    0.38
    ᆫ
    0.38
     пови
    0.36
    чително
    0.36
     만들어
    0.35
    Https
    0.34
    álie
    0.34
    ně
    0.34
    čaj
    0.34
     delimit
    0.34
    POSITIVE LOGITS
    ing
    0.40
    sembling
    0.39
    inating
    0.39
    igating
    0.38
    一定会
    0.36
     کردن
    0.36
    cing
    0.36
    ivating
    0.35
    ):["
    0.35
    abbing
    0.34
    Act Density 0.080%

    No Known Activations