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

    Neuronpedia

    INDEX
    Explanations

    Sketching, code blocks, and descriptive text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     complete
    1.43
    9
    1.37
     full
    1.35
    full
    1.19
    do
    1.19
    he
    1.16
    8
    1.15
    complete
    1.15
     completely
    1.14
    eight
    1.14
    POSITIVE LOGITS
     "./
    1.39
    XPATH
    1.37
    oción
    1.34
    ující
    1.32
    isseurs
    1.32
     vurg
    1.31
    ECM
    1.31
     './
    1.28
    ('./
    1.27
     kavram
    1.27
    Act Density 0.015%

    No Known Activations