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

    Neuronpedia

    INDEX
    Explanations

    numerical values and statistics related to various topics

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

    quantities of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Walkover
    -0.55
     BrowserModule
    -0.52
    UserScript
    -0.47
     ProductService
    -0.45
    AsUp
    -0.45
     WebDriverWait
    -0.43
    istoitu
    -0.42
    Hochspringen
    -0.41
    withOpacity
    -0.40
    CDCl
    -0.39
    POSITIVE LOGITS
     thousands
    0.67
     millions
    0.65
    undred
    0.59
     myſelf
    0.58
     billions
    0.58
     millón
    0.58
    thousands
    0.58
    ousand
    0.56
     hundreds
    0.56
    ſelves
    0.55
    Act Density 0.053%

    No Known Activations