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

    Neuronpedia

    INDEX
    Explanations

    references to demos and examples in various contexts

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

    demo or sample

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IVEREF
    -0.56
    rawDesc
    -0.54
    inSlope
    -0.51
    webElementGuid
    -0.49
     nakalista
    -0.47
     nahilalakip
    -0.47
     térmico
    -0.45
     enfans
    -0.44
     teorías
    -0.43
     vectoriales
    -0.42
    POSITIVE LOGITS
     sample
    0.64
     demonstration
    0.61
     demo
    0.60
     samples
    0.60
     demos
    0.58
     Demo
    0.57
     DEMO
    0.56
    demo
    0.56
    sample
    0.56
     Sample
    0.56
    Act Density 0.125%

    No Known Activations