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

    Neuronpedia

    INDEX
    Explanations

    code structure and variable assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iftoire
    0.38
    <unused210>
    0.38
    Características
    0.36
     क्वेश्चंस
    0.36
    <unused1024>
    0.35
    Antib
    0.35
     niektórych
    0.35
    ﻀ
    0.35
     guérir
    0.34
    uretics
    0.34
    POSITIVE LOGITS
    )
    0.45
    ↵
    0.44
     =
    0.41
     ,
    0.41
       
    0.40
    ,
    0.40
    .
    0.39
     raw
    0.39
     memo
    0.38
    __
    0.38
    Act Density 0.129%

    No Known Activations