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
    Alexander
    -0.07
    ��이
    -0.07
     BDS
    -0.07
    Updated
    -0.06
     exams
    -0.06
     대
    -0.06
    ↵            ↵
    -0.06
    .onActivityResult
    -0.06
    .receiver
    -0.06
    REMOVE
    -0.06
    POSITIVE LOGITS
     Мон
    0.07
     Enterprises
    0.07
    _asm
    0.07
    _rules
    0.07
    desk
    0.06
    _truth
    0.06
    odem
    0.06
     Japon
    0.06
    […
    0.06
    meet
    0.06
    Act Density 0.035%

    No Known Activations