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

    Neuronpedia

    INDEX
    Explanations

    ready

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    channels
    -0.07
     黑
    -0.07
     Landing
    -0.07
    ��索
    -0.07
    提供
    -0.06
     çık
    -0.06
     polishing
    -0.06
    หนอง
    -0.06
    蓝
    -0.06
    üç
    -0.06
    POSITIVE LOGITS
     improbable
    0.07
    ampions
    0.07
    .removeAttribute
    0.06
     Replies
    0.06
    .');↵
    0.06
    .UnitTesting
    0.06
    уг
    0.06
    	if
    0.06
     lucky
    0.06
    (frame
    0.06
    Act Density 0.008%

    No Known Activations