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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to design and compatibility in systems

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

    replacement and interchangeability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.50
    OrWhiteSpace
    -0.38
     OFDb
    -0.38
    Portale
    -0.37
     chofe
    -0.36
    hdessä
    -0.35
     exclusivity
    -0.35
     breathing
    -0.35
     дописавши
    -0.34
     архивлан
    -0.34
    POSITIVE LOGITS
     ujednoznacz
    0.50
     replacement
    0.48
     replacing
    0.47
    SourceChecksum
    0.46
     remplace
    0.46
     Replacing
    0.44
     replacements
    0.44
    replacement
    0.44
     Replacement
    0.43
    Replacing
    0.42
    Act Density 0.094%

    No Known Activations