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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᔾ
    0.76
     ঃ
    0.75
    BURY
    0.74
    ionalmente
    0.74
    uyang
    0.69
    ﻕ
    0.68
    "_
    0.66
    andon
    0.66
    ைகளில்
    0.66
    )_{(
    0.65
    POSITIVE LOGITS
     plywood
    0.79
    嘘
    0.76
    menuStrip
    0.72
    HelloWorld
    0.71
    NSString
    0.69
    मूर्ति
    0.68
     Hello
    0.68
     hello
    0.67
     HelloWorld
    0.67
     Prussian
    0.65
    Act Density 0.059%

    No Known Activations