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

    Neuronpedia

    INDEX
    Explanations

    cited as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     бренда
    0.39
     wardrobe
    0.38
     vestibulum
    0.37
    Underwater
    0.37
     appl
    0.36
     суб
    0.36
    ೀರಿ
    0.36
    ⅞
    0.36
     BRAND
    0.36
     métallique
    0.35
    POSITIVE LOGITS
     Vez
    0.42
    ize
    0.41
     लागत
    0.38
     Synd
    0.37
    stag
    0.37
    utente
    0.37
    टॉप
    0.37
     Vila
    0.36
     vast
    0.36
     Forschung
    0.36
    Act Density 0.000%

    No Known Activations