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

    Neuronpedia

    INDEX
    Explanations

    `renewcommand` for LaTeX macros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pin
    0.56
     বিন্দু
    0.55
    grad
    0.54
    ">•
    0.54
    \\
    0.53
    colon
    0.53
    creatic
    0.53
    }((
    0.52
    Coal
    0.52
     संके
    0.52
    POSITIVE LOGITS
     químicos
    0.70
    ება
    0.70
    რება
    0.68
     Bureau
    0.68
     Fabrication
    0.67
     خاصيه
    0.67
     پروفیسر
    0.66
    ARKS
    0.66
     緑
    0.66
     STRAIGHT
    0.65
    Act Density 0.000%

    No Known Activations