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

    Neuronpedia

    INDEX
    Explanations

    impacts and creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     certains
    0.40
    ಸಿ
    0.40
     Schaden
    0.40
     LinkedIn
    0.40
     сатып
    0.39
     cabe
    0.39
    బడి
    0.38
     Goodwill
    0.38
    తా
    0.37
     FUR
    0.37
    POSITIVE LOGITS
    ylmethylsulfanyl
    0.42
    illation
    0.39
    AccessException
    0.38
     signifies
    0.37
     básicos
    0.37
    yang
    0.36
    的基本
    0.36
    来
    0.36
    animate
    0.36
    ها
    0.35
    Act Density 0.000%

    No Known Activations