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

    Neuronpedia

    INDEX
    Explanations

    common phrases indicating absence or denial

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

    german and danish words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.54
    GEBURTSDATUM
    -0.52
    atia
    -0.49
    IsContent
    -0.46
     invokingState
    -0.44
     HONORABLE
    -0.42
    usercontent
    -0.42
    pexpr
    -0.42
    kua
    -0.41
    WriteTagHelper
    -0.41
    POSITIVE LOGITS
    
    0.51
    ]")]
    0.43
     compréhen
    0.39
    basicConfig
    0.39
    Slf
    0.38
     revés
    0.37
     navideño
    0.37
    🏻
    0.36
    참고
    0.36
     nemlig
    0.36
    Act Density 0.004%

    No Known Activations