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

    Neuronpedia

    INDEX
    Explanations

    references to gems or jewels

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

    gem or gems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.56
     controllable
    -0.51
     langs
    -0.49
    Rourke
    -0.48
     Crouch
    -0.47
     controlling
    -0.46
     controlled
    -0.45
    Nasty
    -0.45
    controlled
    -0.45
    rån
    -0.45
    POSITIVE LOGITS
     Gems
    1.06
     Gem
    1.05
     gems
    1.03
     GEM
    1.01
    Gem
    0.97
     gem
    0.97
    Gems
    0.90
    gems
    0.87
     Gemma
    0.84
     gemstone
    0.83
    Act Density 0.004%

    No Known Activations