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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical models and estimators

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

    regression and estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.61
     myſelf
    -0.48
    ########.
    -0.46
    delwed
    -0.46
     AssemblyCulture
    -0.45
    ’.”
    -0.45
     >=",
    -0.45
     transfieras
    -0.44
     defaultstate
    -0.43
    !!!”
    -0.43
    POSITIVE LOGITS
    :✨
    0.50
    ChildScrollView
    0.45
    UpInside
    0.43
     illustrated
    0.40
     zá
    0.38
     concern
    0.38
    Personendaten
    0.38
     reaching
    0.37
    如下
    0.37
    łku
    0.37
    Act Density 0.524%

    No Known Activations