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

    Neuronpedia

    INDEX
    Explanations

    Acronyms and organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    URED
    -0.07
    ERICA
    -0.06
     Vegan
    -0.06
    KH
    -0.06
     设置
    -0.06
                  
↵
    -0.06
     вклад
    -0.06
    ADF
    -0.06
    customize
    -0.06
     دشمن
    -0.06
    POSITIVE LOGITS
     hardness
    0.07
     chauff
    0.06
    Padding
    0.06
     підвищ
    0.06
     aşağı
    0.06
     gigg
    0.06
    	no
    0.06
     بغ
    0.06
     Ricky
    0.06
    Bottom
    0.06
    Act Density 0.081%

    No Known Activations