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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to conditions and expectations in various contexts

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

    writing or behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementGuid
    -0.53
    principalColumn
    -0.50
     dynamically
    -0.44
     uniformly
    -0.42
    kloped
    -0.41
     extract
    -0.40
     Group
    -0.40
     customized
    -0.40
    pertoire
    -0.39
    agus
    -0.39
    POSITIVE LOGITS
     مشين
    0.54
    rungsseite
    0.51
    hyrchwyd
    0.50
    脚注の使い方
    0.50
    __':
    0.50
    UnsafeEnabled
    0.48
    sizeCache
    0.47
    قایناقلار
    0.47
     disambiguazione
    0.46
    yntaxException
    0.46
    Act Density 0.014%

    No Known Activations