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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or reliance between concepts

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

    not about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.54
    farwyddwr
    -0.43
    办事
    -0.40
    RTLU
    -0.40
    ftagPool
    -0.39
    cuerdo
    -0.39
    Filmografie
    -0.38
    gården
    -0.38
    Insee
    -0.38
    openConnection
    -0.38
    POSITIVE LOGITS
     Italijani
    0.40
     Tanpa
    0.40
    verwijspagina
    0.40
    жели
    0.40
     Notwithstanding
    0.40
    IBOutlet
    0.40
    хьтан
    0.40
     bukanlah
    0.38
     jabón
    0.38
    enumi
    0.38
    Act Density 0.123%

    No Known Activations