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

    Neuronpedia

    INDEX
    Explanations

    references to the paper itself or its contents

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

    a research paper or study

    np_acts-logits-general · gemini-2.0-flash

    this paper or study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.75
     للاسماء
    -0.74
    Personendaten
    -0.73
    getMenuInflater
    -0.69
     referenties
    -0.68
     ostavi
    -0.67
    )++;
    -0.65
    Extinguishing
    -0.64
     BoxDecoration
    -0.64
     незавершена
    -0.63
    POSITIVE LOGITS
     report
    0.62
     campi
    0.52
    ardoor
    0.52
    /**
    0.51
     document
    0.50
     sub
    0.50
     paper
    0.49
    temon
    0.48
    ///</
    0.47
    wegen
    0.46
    Act Density 0.346%

    No Known Activations