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

    Neuronpedia

    INDEX
    Explanations

    numerals and numerical data

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

    6 month follow-up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.42
     alguno
    -0.41
    either
    -0.37
     nélkül
    -0.36
     solchen
    -0.36
    enderita
    -0.36
     murni
    -0.36
    NameInMap
    -0.35
     cuantos
    -0.34
     keinem
    -0.34
    POSITIVE LOGITS
    المناصب
    0.59
    :✨
    0.54
    庁
    0.52
    LookAnd
    0.51
    ᦺ
    0.50
     '{@
    0.49
    arakat
    0.49
    ſelves
    0.48
     eche
    0.47
    𖡻
    0.47
    Act Density 0.048%

    No Known Activations