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

    Neuronpedia

    INDEX
    Explanations

    instances of close competition or tight scores in competitive contexts

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

    close or narrow margins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ੝
    -0.63
     queſta
    -0.63
    MethodManager
    -0.61
     betweenstory
    -0.58
    ंदीखरीदारी
    -0.57
    Cyfarwyddwr
    -0.57
    SourceChecksum
    -0.55
    ſelben
    -0.54
    Джерела
    -0.54
    windowFixed
    -0.54
    POSITIVE LOGITS
     tight
    0.48
     close
    0.38
     Close
    0.36
    tight
    0.36
     taut
    0.35
    verwijspagina
    0.35
     closely
    0.35
    CLOSE
    0.34
    Close
    0.34
     tense
    0.33
    Act Density 0.022%

    No Known Activations