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

    Neuronpedia

    INDEX
    Explanations

    no arrest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сну
    0.50
    حدة
    0.45
     karşınız
    0.45
    ρον
    0.45
     аласыз
    0.45
    𝙛
    0.44
     που
    0.42
    ாளர்
    0.42
    ğiniz
    0.42
    ﻓ
    0.42
    POSITIVE LOGITS
     each
    0.42
     وصول
    0.41
     microscopic
    0.41
    each
    0.40
     Ha
    0.40
     emphasis
    0.38
     avvic
    0.38
    WR
    0.38
     প্রত্যেক
    0.37
    Ha
    0.37
    Act Density 0.007%

    No Known Activations