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

    Neuronpedia

    INDEX
    Explanations

    correctness and manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     optimism
    1.05
     and
    1.05
     compassion
    1.04
     unprecedented
    1.03
     incredible
    1.00
     six
    0.98
     unplanned
    0.97
     our
    0.96
     unparalleled
    0.93
     ambition
    0.92
    POSITIVE LOGITS
    drawiam
    1.01
     Gradle
    0.90
    )。
    0.90
     angegeben
    0.88
     použití
    0.87
    መሪያ
    0.87
    場合
    0.87
     möglicherweise
    0.86
     Operand
    0.86
    Syntax
    0.85
    Act Density 1.277%

    No Known Activations