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

    Neuronpedia

    INDEX
    Explanations

    married men

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ascended
    1.01
    ist
    1.00
     rah
    0.96
    话
    0.96
     तारीफ
    0.93
     holders
    0.93
    ate
    0.91
    0
    0.90
    <0xAF>
    0.90
    iga
    0.89
    POSITIVE LOGITS
    lamide
    1.33
    SVM
    1.22
    essex
    1.21
    があります
    1.19
    eses
    1.19
    cubic
    1.15
     mandib
    1.14
    eol
    1.14
     tume
    1.13
    لنا
    1.13
    Act Density 0.000%

    No Known Activations