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

    Neuronpedia

    INDEX
    Explanations

    static, lasers, forever, name, common, weigh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ហើយ
    0.37
     정확
    0.36
    正確
    0.36
    威
    0.35
     birefringence
    0.35
    精准
    0.35
     operatives
    0.35
    Comm
    0.34
     родствен
    0.34
    配列
    0.33
    POSITIVE LOGITS
     Nico
    0.42
    ('',
    0.42
    ùng
    0.40
     решить
    0.39
     kú
    0.39
    ière
    0.38
     koş
    0.38
     exit
    0.38
     Coco
    0.38
     pk
    0.37
    Act Density 0.000%

    No Known Activations