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

    Neuronpedia

    INDEX
    Explanations

    text fragments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (|\
    0.61
    точно
    0.58
    OB
    0.54
    energia
    0.52
    UPDATE
    0.52
    ORDER
    0.52
    sandwich
    0.50
    ريكية
    0.50
    SIX
    0.50
     الطاقة
    0.49
    POSITIVE LOGITS
     esos
    0.64
     tons
    0.61
     acres
    0.59
    锈
    0.59
    गोल
    0.58
     fraught
    0.57
    ष्ट
    0.56
     wicket
    0.56
    äft
    0.56
     weatherproof
    0.56
    Act Density 0.000%

    No Known Activations