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

    Neuronpedia

    INDEX
    Explanations

    walls and barriers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adık
    -0.07
    ації
    -0.07
    aceutical
    -0.06
     technical
    -0.06
    Les
    -0.06
     training
    -0.06
    Tw
    -0.06
     poisoning
    -0.06
    ATION
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    اضي
    0.07
    ラン
    0.06
     segreg
    0.06
     Illustrator
    0.06
     등록
    0.06
     قیمت
    0.06
    ýn
    0.06
     security
    0.06
    ज़
    0.06
    MEDIA
    0.06
    Act Density 0.029%

    No Known Activations