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

    Neuronpedia

    INDEX
    Explanations

    classes, items, and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     א
    0.32
    För
    0.29
     전
    0.29
    שי
    0.27
    众多
    0.26
     sõ
    0.25
     с
    0.24
    ง
    0.24
     izay
    0.24
    积极
    0.24
    POSITIVE LOGITS
    !:
    0.31
    estruct
    0.29
    っぽい
    0.29
     ജെ
    0.27
    ieval
    0.27
    aulay
    0.27
    ieux
    0.26
    द्व
    0.26
     avevano
    0.26
    ureate
    0.26
    Act Density 0.000%

    No Known Activations