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

    Neuronpedia

    INDEX
    Explanations

    words that indicate quantities or numerical references

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

    Following "The" or "the"

    np_acts-logits-general · gemini-2.0-flash

    technical specifications and correctness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fVar
    -0.59
     preguntar
    -0.59
     scrolls
    -0.55
     AppColors
    -0.55
    chmal
    -0.53
    joys
    -0.52
     imprese
    -0.52
     scuole
    -0.51
     MessageType
    -0.49
     nadzieję
    -0.49
    POSITIVE LOGITS
     ProtoMessage
    0.68
     algorithm
    0.67
     appropriate
    0.67
     following
    0.64
     corrispond
    0.64
     desired
    0.61
    AdapterFactory
    0.60
     actual
    0.60
    _()
    0.59
     corret
    0.58
    Act Density 0.589%

    No Known Activations