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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical actions and their implications

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

    European or German content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.75
    таратура
    -0.64
     kasarigan
    -0.64
    SharedDtor
    -0.64
     BrowserModule
    -0.59
    ReusableCell
    -0.57
    出版年
    -0.57
    SharedCtor
    -0.56
    IBOutlet
    -0.55
     AspNetCore
    -0.52
    POSITIVE LOGITS
    因
    0.35
     Sorge
    0.34
     further
    0.34
    ectady
    0.33
    Insee
    0.33
     Vogel
    0.32
    ])[
    0.31
     Gesicht
    0.31
     Meinung
    0.30
     Schicht
    0.30
    Act Density 0.018%

    No Known Activations