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

    Neuronpedia

    INDEX
    Explanations

    programming function and class declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jury
    0.42
     juries
    0.39
    })(\
    0.39
     oversees
    0.38
     masks
    0.37
    jury
    0.36
     corpses
    0.36
     substitutes
    0.36
    scdn
    0.36
    邸
    0.36
    POSITIVE LOGITS
    Hello
    0.99
     hello
    0.98
    hello
    0.96
     Hello
    0.96
    HelloWorld
    0.91
     HelloWorld
    0.81
     foo
    0.79
     Greeting
    0.79
     ejemplo
    0.78
     saludar
    0.77
    Act Density 0.062%

    No Known Activations