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

    Neuronpedia

    INDEX
    Explanations

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，如果
    -0.06
    >
↵
↵
    -0.06
                   
↵
    -0.06
                  
↵
    -0.06
    ชม
    -0.06
     filmmaker
    -0.06
     gatherings
    -0.06
    .UnitTesting
    -0.06
    くれ
    -0.06
    ！”↵↵
    -0.06
    POSITIVE LOGITS
    형
    0.07
    ρός
    0.07
     rupt
    0.06
     salty
    0.06
    ože
    0.06
    型
    0.06
    规
    0.06
    \web
    0.06
    영
    0.06
    (TreeNode
    0.06
    Act Density 0.000%

    No Known Activations