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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or trade-offs in processes or comparisons

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

    depending on outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.47
     ब्रेकडाउन
    -0.44
    MemoryWarning
    -0.42
     للمعارف
    -0.41
     AssemblyCompany
    -0.40
    DeleteBehavior
    -0.39
     HttpNotFound
    -0.37
     autorytatywna
    -0.35
    Bronnen
    -0.35
     Labeling
    -0.35
    POSITIVE LOGITS
     depending
    0.49
     Depending
    0.45
    Depending
    0.45
     options
    0.45
     dependiendo
    0.43
     differ
    0.42
     choices
    0.41
    ければ
    0.40
     depender
    0.40
     differs
    0.40
    Act Density 0.086%

    No Known Activations