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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which" and its variations in relation to contextual explanations

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

    contrast or exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viewDidLoad
    -0.46
    Hozzáférés
    -0.43
    httphttps
    -0.42
    encodeWith
    -0.42
    Personendaten
    -0.41
     Suits
    -0.38
    viewDidLoad
    -0.36
    İstinadlar
    -0.36
    出版年
    -0.36
    uesia
    -0.35
    POSITIVE LOGITS
    rungsseite
    0.60
     Exacts
    0.49
     Reverso
    0.45
    TryDecodeAsNil
    0.42
    kháu
    0.42
    Тарихы
    0.41
     bitte
    0.41
     yaiba
    0.41
    EndGlobalSection
    0.40
     Infórmanos
    0.39
    Act Density 0.129%

    No Known Activations