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

    Neuronpedia

    INDEX
    Explanations

    AI and language models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     образования
    -0.08
    stdout
    -0.07
    xor
    -0.07
     tbl
    -0.07
    "){
↵
    -0.07
    Vars
    -0.07
    आई
    -0.07
    addComponent
    -0.06
    ｜
    -0.06
     Throw
    -0.06
    POSITIVE LOGITS
    issional
    0.07
     Kimber
    0.06
     obtaining
    0.06
    租
    0.06
     Desktop
    0.06
     Context
    0.06
     목
    0.06
     ש
    0.06
    itect
    0.05
    概念
    0.05
    Act Density 0.016%

    No Known Activations