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

    Neuronpedia

    INDEX
    Explanations

    dive into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ご了承ください
    0.43
     Contributing
    0.42
    ◈
    0.39
     STL
    0.38
    玧
    0.37
     Kontakt
    0.37
     Linking
    0.36
    getBody
    0.36
     Boundary
    0.35
     فلم
    0.35
    POSITIVE LOGITS
    ষ্ক
    0.40
    रान
    0.40
     rind
    0.40
     प्रशा
    0.39
    туи
    0.38
    FindBy
    0.38
     digo
    0.37
     sudah
    0.37
    pras
    0.37
     सीट
    0.37
    Act Density 0.000%

    No Known Activations