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

    Neuronpedia

    INDEX
    Explanations

    references to withdrawal or absence of something significant

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

    genie and arabian contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     怎样
    -0.41
     tričko
    -0.39
    UnusedPrivate
    -0.37
    writerow
    -0.36
     überw
    -0.35
    ɵ
    -0.35
     arşivlendi
    -0.34
     llanto
    -0.34
     čin
    -0.33
    nant
    -0.33
    POSITIVE LOGITS
     genie
    1.02
     Aladdin
    0.95
    Aladdin
    0.89
     Arabian
    0.85
    🧞
    0.82
     Genie
    0.81
    genie
    0.75
    Arab
    0.74
    Genie
    0.73
     arab
    0.71
    Act Density 0.023%

    No Known Activations