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

    Neuronpedia

    INDEX
    Explanations

    numerical values and the presence of periods

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

    end of list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.85
     мәкал
    -0.81
    IUrlHelper
    -0.73
    httphttps
    -0.72
    ImageContext
    -0.68
     utafitiHapana
    -0.64
     useAppContext
    -0.63
     Мексичка
    -0.63
    ագրություններ
    -0.61
     queſta
    -0.60
    POSITIVE LOGITS
    Và
    0.42
     infine
    0.34
    Datuak
    0.33
     Finally
    0.33
     posible
    0.31
    AndWait
    0.31
     lastly
    0.31
    それに
    0.31
     biti
    0.30
     Ciencia
    0.30
    Act Density 0.039%

    No Known Activations