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

    Neuronpedia

    INDEX
    Explanations

    fastest air, cost of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     refrain
    0.40
    的效果
    0.40
    鉤
    0.39
    raiser
    0.39
     कारण
    0.39
     konz
    0.37
    atr
    0.37
    防止
    0.37
    িকারী
    0.36
     soddisf
    0.36
    POSITIVE LOGITS
     murals
    0.47
    벽
    0.44
     BR
    0.41
    жному
    0.40
     BBM
    0.40
    ্জ
    0.39
    であることが
    0.39
     BALL
    0.39
     Emerg
    0.39
     иң
    0.39
    Act Density 0.000%

    No Known Activations