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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "include" and its variations, highlighting lists or mentions of entities

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

    listing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zám
    -0.40
    此
    -0.38
     yaptığı
    -0.38
    omości
    -0.37
    ubre
    -0.36
     terjadi
    -0.36
     void
    -0.35
     此
    -0.35
    它
    -0.35
     Sebuah
    -0.34
    POSITIVE LOGITS
     pharmacists
    0.64
    InjectMocks
    0.61
    orianCalendar
    0.60
    someone
    0.60
    individuals
    0.59
     journalists
    0.59
    usercontent
    0.59
    Personendaten
    0.59
    Personensuche
    0.59
    MemoryWarning
    0.59
    Act Density 0.032%

    No Known Activations