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

    Neuronpedia

    INDEX
    Explanations

    complex relationships and dependencies in arguments or concepts

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

    purpose, problem, goal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.50
    beginTransaction
    -0.47
    الإنجليزية
    -0.45
    RetentionPolicy
    -0.44
     Robust
    -0.44
     GenerationType
    -0.44
    AnchorStyles
    -0.43
     Fath
    -0.43
    bootstrapcdn
    -0.43
     Lein
    -0.42
    POSITIVE LOGITS
     '\\;'
    0.46
    bewerken
    0.40
     dasarnya
    0.38
     spørgsmål
    0.38
     underlying
    0.37
    Essentially
    0.36
     funda
    0.35
     fundamentally
    0.35
     ans
    0.35
    const
    0.34
    Act Density 0.069%

    No Known Activations