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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to modeling and performance metrics in engineering contexts

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

    geometry and design of models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -0.45
     cauſe
    -0.45
     tranſ
    -0.44
    FunctionFlags
    -0.44
    NameInMap
    -0.43
     faſt
    -0.42
    OGND
    -0.42
    httphttps
    -0.42
     ſeveral
    -0.42
     juſt
    -0.42
    POSITIVE LOGITS
     design
    0.66
     designs
    0.61
     DESIGN
    0.52
     diseños
    0.51
     designed
    0.51
    设计
    0.50
    InputBorder
    0.50
     Design
    0.50
     designing
    0.50
     constructed
    0.49
    Act Density 0.095%

    No Known Activations