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

    Neuronpedia

    INDEX
    Explanations

    closing braces in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebVitals
    -0.45
     nahilalakip
    -0.42
     ditto
    -0.41
     PropertyChanged
    -0.40
    pagin
    -0.40
     peg
    -0.40
    SaveVideo
    -0.40
     thunk
    -0.39
     lenker
    -0.39
    mbggenerated
    -0.39
    POSITIVE LOGITS
     mukaan
    0.43
     käyttö
    0.42
     kasarigan
    0.41
    versies
    0.41
    esistenza
    0.40
    (!__
    0.40
    indirizzo
    0.40
     aikaa
    0.40
    '])){
    0.39
    ↵↵↵↵↵
    0.39
    Act Density 0.001%

    No Known Activations