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

    Neuronpedia

    INDEX
    Explanations

    collaboration and working together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    大
    1.09
    ра
    1.01
     on
    1.00
    د
    0.94
    ۲
    0.89
    𝟮
    0.89
    ریان
    0.88
    .
    0.87
    ד
    0.83
    ある
    0.81
    POSITIVE LOGITS
    ু
    1.11
    i
    1.09
    та
    1.08
     Collaborate
    1.06
    지
    1.06
    트
    1.05
    ي
    1.04
    <0x0D>
    0.98
    ant
    0.95
    ങ്ങൾ
    0.95
    Act Density 0.010%

    No Known Activations