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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vatican
    -0.07
     such
    -0.07
    .GREEN
    -0.07
    .attrib
    -0.07
    ！”↵↵
    -0.06
     datab
    -0.06
     DLC
    -0.06
    =%.
    -0.06
     finde
    -0.06
     ήταν
    -0.06
    POSITIVE LOGITS
     saison
    0.06
    names
    0.06
     чин
    0.06
    _procs
    0.06
     flex
    0.05
    ?>
↵
    0.05
    .grid
    0.05
     arresting
    0.05
    yahoo
    0.05
    �
    0.05
    Act Density 0.000%

    No Known Activations