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

    Neuronpedia

    INDEX
    Explanations

    letters to the editor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blanc
    -0.07
     מבוס
    -0.07
    thon
    -0.07
    ográf
    -0.07
    IGNAL
    -0.07
    ยาว
    -0.07
    	field
    -0.07
    "g
    -0.06
     ayr
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    .sprites
    0.08
    dot
    0.07
    开始
    0.07
     Hoffman
    0.07
    ₍
    0.07
     swagger
    0.07
    _decorator
    0.07
    {}_
    0.07
     ---↵
    0.07
    django
    0.07
    Act Density 0.003%

    No Known Activations