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

    Neuronpedia

    INDEX
    Explanations

    ads, content, webcam, packs, copyrighted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gauche
    0.38
    achtig
    0.36
     retard
    0.35
    దే
    0.35
     izquierda
    0.35
     нач
    0.35
    slidesPerView
    0.35
    ᴾ
    0.34
     ಶು
    0.33
     самом
    0.33
    POSITIVE LOGITS
     Lining
    0.38
     liner
    0.37
    ینس
    0.37
    oe
    0.36
    цима
    0.36
    atação
    0.36
     OE
    0.36
    ٫
    0.36
    Constructor
    0.35
     Liner
    0.35
    Act Density 0.000%

    No Known Activations