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

    Neuronpedia

    INDEX
    Explanations

    Offer unwavering, HR drives, Ensure the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aimana
    0.38
     false
    0.38
    violin
    0.38
    anoic
    0.37
     নৃশংস
    0.37
    ഫോ
    0.37
    ྞ
    0.37
    ámicas
    0.36
    youtube
    0.36
    oxic
    0.36
    POSITIVE LOGITS
     kaks
    0.41
    成像
    0.39
    র্ক
    0.38
     輸入
    0.36
     LocalDate
    0.36
     脱
    0.35
     ste
    0.35
     circun
    0.35
     помі
    0.35
    ומ
    0.34
    Act Density 0.000%

    No Known Activations