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

    Neuronpedia

    INDEX
    Explanations

    cause-and-effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poses
    1.02
     aides
    1.01
     FY
    0.99
     Chakraborty
    0.96
     Centennial
    0.94
     équipe
    0.93
    itake
    0.92
     bearers
    0.90
     pose
    0.89
    ◄
    0.89
    POSITIVE LOGITS
    ว
    1.19
    ี่
    1.17
     був
    1.14
     lẻ
    1.10
    व
    1.07
     увели
    1.05
    व्ह
    1.03
    ック
    1.01
    類
    1.01
    ͝
    1.00
    Act Density 0.000%

    No Known Activations