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

    Neuronpedia

    INDEX
    Explanations

    references to star ratings and rankings

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

    star ratings and quality grades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.42
    Примітки
    -0.37
    Географија
    -0.36
     ucapnya
    -0.34
     uska
    -0.28
    ValueStyle
    -0.28
    iastes
    -0.28
    ISD
    -0.27
     szóci
    -0.26
    roach
    -0.26
    POSITIVE LOGITS
     star
    0.75
    星
    0.71
     Star
    0.71
     STAR
    0.68
     Stars
    0.68
     stars
    0.68
    starred
    0.64
    ★★★★
    0.63
    Star
    0.63
     sterren
    0.62
    Act Density 0.066%

    No Known Activations