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

    Neuronpedia

    INDEX
    Explanations

    hello greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kam
    0.40
     wan
    0.39
     Ait
    0.38
     alb
    0.38
     Karam
    0.38
     Karim
    0.37
     trap
    0.37
     Kam
    0.37
    Kam
    0.37
     Samm
    0.37
    POSITIVE LOGITS
    Holy
    0.45
     hello
    0.44
     Hello
    0.44
    Hello
    0.43
     Bots
    0.42
     Holy
    0.40
     Gwyn
    0.39
     clung
    0.39
    openai
    0.39
    螈
    0.39
    Act Density 0.006%

    No Known Activations