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

    Neuronpedia

    INDEX
    Explanations

    references and instructions related to specific API functionalities

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

    you want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Privacidade
    -0.47
     AttributeSet
    -0.46
     فريبيس
    -0.41
    لينكات
    -0.36
    Bronnen
    -0.36
     سكانية
    -0.35
     للاسماء
    -0.33
    InstrumentedTest
    -0.33
    VersionUID
    -0.33
    tagHelperRunner
    -0.33
    POSITIVE LOGITS
    <?
    0.52
     للمعارف
    0.48
     temat
    0.46
    \{\\
    0.46
     Azad
    0.45
    delwed
    0.44
     importe
    0.43
     świ
    0.43
     kom
    0.43
     Entfernung
    0.43
    Act Density 0.288%

    No Known Activations