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

    Neuronpedia

    INDEX
    Explanations

    guidance on professional etiquette and communications

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

    Follows etiquette rules or advice

    np_acts-logits-general · gemini-2.0-flash

    etiquette or warning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTEE
    -0.75
    migrationBuilder
    -0.70
     препратки
    -0.68
    OGND
    -0.66
    ihnachten
    -0.65
    تقاوى
    -0.63
    脚注の使い方
    -0.59
     externi
    -0.59
     pertanto
    -0.59
     esternos
    -0.59
    POSITIVE LOGITS
     Get
    0.63
     it
    0.62
     they
    0.62
     get
    0.60
     ‘
    0.59
    </h1>
    0.58
     They
    0.57
     …
    0.56
     its
    0.53
    Get
    0.53
    Act Density 0.073%

    No Known Activations