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

    Neuronpedia

    INDEX
    Explanations

    hello world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    燭
    0.40
     EQ
    0.39
    Zs
    0.37
     Lept
    0.37
     लहंगा
    0.36
    RH
    0.36
    LAGAB
    0.36
    IONS
    0.36
     clothing
    0.36
    PEND
    0.36
    POSITIVE LOGITS
     👋
    1.02
     hello
    0.99
     Hello
    0.99
    Hello
    0.98
     world
    0.95
     greetings
    0.93
     mundo
    0.90
    hello
    0.90
     мире
    0.89
     dunia
    0.89
    Act Density 0.047%

    No Known Activations