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

    Neuronpedia

    INDEX
    Explanations

    try to explain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     debtors
    0.50
    公司的
    0.50
    GRO
    0.48
    company
    0.47
    CHESTER
    0.47
    ittances
    0.47
    ınız
    0.46
    ENTES
    0.46
    owner
    0.46
    "@
    0.46
    POSITIVE LOGITS
     сложных
    0.47
     exploration
    0.46
     گوئی
    0.46
     آر
    0.45
     filmed
    0.44
    좔
    0.44
     |.
    0.43
    茠
    0.43
     Perkin
    0.43
     Markup
    0.43
    Act Density 0.001%

    No Known Activations