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

    Neuronpedia

    INDEX
    Explanations

    artificial intelligent assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TRAN
    0.33
    行走
    0.33
    <start_of_image>
    0.33
    บ้าน
    0.31
    gradation
    0.31
     এড
    0.31
     геро
    0.31
     الفنان
    0.31
    コミュニ
    0.31
    伏
    0.30
    POSITIVE LOGITS
    Aula
    0.39
    ář
    0.38
     Nasr
    0.37
    ^*(
    0.37
     À
    0.37
     eSIM
    0.36
     ù
    0.35
     KSI
    0.35
     Ə
    0.35
     pulp
    0.35
    Act Density 0.269%

    No Known Activations