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

    Neuronpedia

    INDEX
    Explanations

    phrases related to database functionality and limitations

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

    zur Verfügung

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.49
     nothwendig
    -0.49
    AddTagHelper
    -0.48
    antaranya
    -0.47
     GenerationType
    -0.46
     tiguan
    -0.46
     itſelf
    -0.46
     citoy
    -0.46
     fubject
    -0.45
     zijne
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.48
     RE
    0.44
     fus
    0.44
     RECOMMENDED
    0.43
     BELOW
    0.43
    Mok
    0.43
     Oma
    0.42
     Mok
    0.42
    ns
    0.42
    斯卡
    0.41
    Act Density 0.017%

    No Known Activations