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

    Neuronpedia

    INDEX
    Explanations

    code comments/keywords

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xuống
    -0.08
    KeyId
    -0.07
     hiç
    -0.07
    户籍
    -0.07
    apses
    -0.07
    =e
    -0.07
    Git
    -0.07
    神州
    -0.07
    很小
    -0.07
    ꦮ
    -0.06
    POSITIVE LOGITS
    tre
    0.07
    	register
    0.07
    ।
    0.07
     traverse
    0.07
    !,
    0.07
    ","
    0.06
     ←
    0.06
    𝅎
    0.06
    </
    0.06
    قص
    0.06
    Act Density 0.001%

    No Known Activations