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

    Neuronpedia

    INDEX
    Explanations

    references to education and training backgrounds

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

    tradition and origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.56
    MLLoader
    -0.51
    ConstraintMaker
    -0.51
    ftagPool
    -0.51
    OGND
    -0.51
     purpoſe
    -0.51
    neſs
    -0.50
    MemoryWarning
    -0.50
    TagMode
    -0.49
    principalColumn
    -0.49
    POSITIVE LOGITS
     Herkunft
    0.48
     orígenes
    0.45
    出身
    0.44
     derivados
    0.41
     Konkurrenz
    0.41
     tradição
    0.40
    derived
    0.38
    Derived
    0.38
     derived
    0.38
     tradizione
    0.37
    Act Density 0.051%

    No Known Activations