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

    Neuronpedia

    INDEX
    Explanations

    concepts related to understanding relationships and communication in various contexts

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

    understanding and signaling insights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.54
    HandlerContext
    -0.48
    aarrggbb
    -0.47
    ronpa
    -0.44
    RegressionTest
    -0.43
     otomatig
    -0.41
     pitting
    -0.41
    PerformLayout
    -0.41
    prepareStatement
    -0.41
     שמ
    -0.40
    POSITIVE LOGITS
     arginine
    0.37
     strå
    0.37
     hjär
    0.37
     braço
    0.36
    displaymath
    0.36
     girasol
    0.36
    texpr
    0.35
    Fisher
    0.35
     Arab
    0.35
    erequisite
    0.35
    Act Density 0.320%

    No Known Activations