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

    Neuronpedia

    INDEX
    Explanations

    askingfor?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    1.01
    maları
    0.89
    aç
    0.88
    ać
    0.87
     kembali
    0.87
     органів
    0.86
     ettevõ
    0.85
     betekent
    0.85
     systemu
    0.85
    ي
    0.85
    POSITIVE LOGITS
    Hob
    0.73
    ریز
    0.72
    CH
    0.65
    chino
    0.64
     overpowering
    0.62
    Fry
    0.62
    TTY
    0.61
     میکس
    0.61
     just
    0.61
    राधिक
    0.60
    Act Density 0.748%

    No Known Activations