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

    Neuronpedia

    INDEX
    Explanations

    protected characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DEV
    0.40
     env
    0.39
    跑步
    0.38
    亙
    0.38
     lettera
    0.37
     thermodynam
    0.37
    ivided
    0.36
     types
    0.36
     letra
    0.36
     volatiles
    0.36
    POSITIVE LOGITS
     장애
    0.52
     gender
    0.51
     disability
    0.48
     الجنس
    0.47
     religion
    0.46
    gender
    0.46
     creed
    0.44
     Disabilities
    0.44
     Gender
    0.43
     orientación
    0.42
    Act Density 0.003%

    No Known Activations