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

    Neuronpedia

    INDEX
    Explanations

    male or female entity names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polluting
    0.84
     rebates
    0.80
    ITE
    0.78
    pstmt
    0.76
     shearing
    0.76
    ಕ್‌
    0.75
    并购
    0.75
     manure
    0.75
     malpractice
    0.74
    త్మిక
    0.74
    POSITIVE LOGITS
     وق
    0.73
    ocie
    0.67
     गिलास
    0.67
     titular
    0.66
    ли
    0.65
     fach
    0.65
    am
    0.64
     ",
    0.63
    是因為
    0.63
     নাটক
    0.62
    Act Density 0.001%

    No Known Activations