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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RAID
    -0.07
     sağlık
    -0.07
     Ihnen
    -0.07
    -themed
    -0.06
     cabin
    -0.06
     parenting
    -0.06
     Genius
    -0.06
    Prince
    -0.06
    ふ
    -0.06
    auge
    -0.06
    POSITIVE LOGITS
     pravděpodob
    0.07
     @{↵
    0.07
    Attempt
    0.06
     ];
↵
    0.06
    relude
    0.06
    encoding
    0.06
    ++++++++
    0.06
    Begin
    0.06
    {(
    0.06
    unsqueeze
    0.06
    Act Density 0.011%

    No Known Activations