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

    Neuronpedia

    INDEX
    Explanations

    safe abortion, project requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.61
    )
    0.57
    ata
    0.55
    but
    0.53
    cake
    0.52
    domain
    0.50
    sensor
    0.49
    on
    0.48
    platinum
    0.48
    nya
    0.47
    POSITIVE LOGITS
     Koles
    0.52
    роў
    0.50
     परिवेश
    0.49
    信念
    0.48
    更快
    0.47
    ेंट्स
    0.47
     الأرض
    0.47
    ሎች
    0.47
    婪
    0.47
     ইন্ডাস্ট
    0.46
    Act Density 0.000%

    No Known Activations