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

    Neuronpedia

    INDEX
    Explanations

    phrases related to critical analyses of societal issues, particularly focusing on judgments and consequences

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

    important part itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Попис
    -0.40
    Tembelea
    -0.38
     (;;)
    -0.38
     محفوظة
    -0.37
     CommonModule
    -0.37
    (;;)
    -0.37
     AssemblyVersion
    -0.36
     Speech
    -0.35
    FieldBuilder
    -0.35
     Roskov
    -0.35
    POSITIVE LOGITS
     فريبيس
    0.47
    蚪
    0.46
    ++];
    0.45
    GEBURTSDATUM
    0.43
     <>",
    0.43
     ""],
    0.41
    ScopeManager
    0.41
     execution
    0.39
     snowball
    0.39
    tifacts
    0.39
    Act Density 0.056%

    No Known Activations