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

    Neuronpedia

    INDEX
    Explanations

    references to materials and their attributes in various contexts

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

    materials and their descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.66
     AssemblyVersion
    -0.59
    DeleteBehavior
    -0.52
     ModelExpression
    -0.50
    WriteAttribute
    -0.50
    曖昧さ回避
    -0.49
    obby
    -0.48
     RISERV
    -0.47
    toHave
    -0.46
     bParam
    -0.46
    POSITIVE LOGITS
     materials
    0.75
     Materials
    0.75
    Materials
    0.74
    materials
    0.69
     matériaux
    0.66
     materialen
    0.63
     MATERIALS
    0.57
    MATERIALS
    0.57
     materiali
    0.57
     materiales
    0.56
    Act Density 0.018%

    No Known Activations