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

    Neuronpedia

    INDEX
    Explanations

    is be a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encoder
    -0.07
    embro
    -0.07
    τικά
    -0.07
    theorem
    -0.06
     FO
    -0.06
    ीध
    -0.06
    ��
    -0.06
    ंडल
    -0.06
    avou
    -0.06
    љ
    -0.06
    POSITIVE LOGITS
     stabbed
    0.07
     exile
    0.07
     settlements
    0.07
    .load
    0.07
    /article
    0.07
     pozn
    0.06
    Prot
    0.06
     příležit
    0.06
     guitar
    0.06
     lifes
    0.06
    Act Density 0.115%

    No Known Activations