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

    Neuronpedia

    INDEX
    Explanations

    British aristocracy names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Title
    -0.07
    녕
    -0.07
    友好
    -0.07
    goods
    -0.07
    InteractionEnabled
    -0.07
    	length
    -0.06
     encoder
    -0.06
     secret
    -0.06
     corresponds
    -0.06
    팀
    -0.06
    POSITIVE LOGITS
    如何看待
    0.07
    (".");↵
    0.07
    چ
    0.07
    OE
    0.07
    arence
    0.07
    CHE
    0.06
     בלוג
    0.06
    (PC
    0.06
    矶
    0.06
     <?=
    0.06
    Act Density 0.025%

    No Known Activations