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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to specific amounts or identifiers

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

    website URLs, phone numbers, code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Klassi
    -0.35
     originating
    -0.34
     origines
    -0.33
     signalled
    -0.32
     للمعارف
    -0.32
    ígenes
    -0.32
     attack
    -0.32
     taraf
    -0.31
     cherchez
    -0.31
     cercana
    -0.31
    POSITIVE LOGITS
     BoxFit
    0.57
    SpringBootTest
    0.54
    ymce
    0.53
     $_"
    0.53
    +:+
    0.53
    HideFlags
    0.53
    ViewFeatures
    0.52
    leſs
    0.52
     argint
    0.52
     groupBox
    0.50
    Act Density 0.044%

    No Known Activations