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
     Advent
    -0.06
    then
    -0.06
     Carb
    -0.06
    "]);
↵
    -0.06
     Salv
    -0.06
     หล
    -0.06
    unning
    -0.06
    )");↵↵
    -0.06
     ब
    -0.06
    يمة
    -0.06
    POSITIVE LOGITS
    bounded
    0.07
    적인
    0.07
    iversite
    0.06
    procedure
    0.06
    不足
    0.06
     tortured
    0.06
    咨
    0.06
    _factor
    0.06
    Taylor
    0.06
     economically
    0.06
    Act Density 0.107%

    No Known Activations