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

    Neuronpedia

    INDEX
    Explanations

    granted access, perfect drink

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    楽天
    0.42
    ද
    0.42
    ьогодні
    0.41
     jog
    0.40
    oc
    0.39
     जाल
    0.37
    ੴ
    0.37
    ക്ടര്‍
    0.37
     cadet
    0.37
     جاسک
    0.36
    POSITIVE LOGITS
     বুঝিয়ে
    0.39
     Languages
    0.39
     languages
    0.37
    ButtonClicked
    0.37
    绑
    0.37
    ína
    0.36
    বির
    0.36
     windowsill
    0.36
    뷌
    0.35
    inations
    0.35
    Act Density 0.000%

    No Known Activations