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

    Neuronpedia

    INDEX
    Explanations

    concepts related to analysis and evaluation processes

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

    performing an analysis or test

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    が
    -0.39
     beig
    -0.35
     ways
    -0.32
    running
    -0.32
     Fac
    -0.32
     CFA
    -0.32
     Италијани
    -0.32
     police
    -0.31
     SOU
    -0.30
     life
    -0.30
    POSITIVE LOGITS
    findpost
    0.59
     disambiguazione
    0.57
    PerformLayout
    0.53
    WebElementEntity
    0.52
    principalColumn
    0.52
    :✨
    0.50
    μιουργ
    0.49
    TestingModule
    0.48
     للاسماء
    0.48
    BeginInit
    0.48
    Act Density 0.138%

    No Known Activations