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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or moral judgments

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

    negative outcomes and important indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.65
    iettes
    -0.48
    seiti
    -0.47
     loopholes
    -0.45
    monary
    -0.45
    flich
    -0.44
    あく
    -0.44
     flashback
    -0.44
     unload
    -0.44
     fluctuate
    -0.43
    POSITIVE LOGITS
    RTLR
    0.53
    AntiForgeryToken
    0.50
     Jefus
    0.49
     ویکی‌پدیا
    0.47
     kasarigan
    0.47
     doInBackground
    0.46
     disambiguazione
    0.46
    BeginInit
    0.42
     humains
    0.42
     abſ
    0.41
    Act Density 0.089%

    No Known Activations