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

    Neuronpedia

    INDEX
    Explanations

    include

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を与
    0.77
    CBPeripheral
    0.63
     ಪರ
    0.62
    かで
    0.62
    よりも
    0.62
    ठीक
    0.61
    හෙ
    0.61
    sprech
    0.61
    ल्लिंग
    0.61
     Operate
    0.60
    POSITIVE LOGITS
     include
    5.92
     includes
    5.83
     including
    5.38
    include
    5.31
    includes
    5.24
     Includes
    5.22
     Include
    5.22
    Includes
    5.21
    Include
    5.15
     incluye
    5.12
    Act Density 2.549%

    No Known Activations