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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or appreciation

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

    need anything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alinga
    -0.36
     Bundy
    -0.35
    speak
    -0.35
    HOLD
    -0.34
    spa
    -0.34
     Ey
    -0.34
     progres
    -0.34
    sti
    -0.34
    佗
    -0.33
     effort
    -0.33
    POSITIVE LOGITS
    RegistryLite
    0.67
    0.60
    enumii
    0.56
    kheim
    0.54
    makeConstraints
    0.54
     StatefulWidget
    0.54
     JpaRepository
    0.52
     dezelve
    0.52
     zelve
    0.52
     AssemblyCompany
    0.50
    Act Density 0.051%

    No Known Activations