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

    Neuronpedia

    INDEX
    Explanations

    the token "user" in various contexts

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

    words starting with d

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     continúas
    -0.35
    setAccessible
    -0.35
    뀐
    -0.33
    ForValue
    -0.32
    斂
    -0.32
     parvenir
    -0.30
    敛
    -0.30
    Мы
    -0.29
    thenReturn
    -0.29
     CanadaChoose
    -0.29
    POSITIVE LOGITS
     يتيمه
    0.71
    istoitu
    0.64
     AssemblyTitle
    0.61
    دانشنامهٔ
    0.57
    StoreMessageInfo
    0.57
     ErrIntOverflow
    0.56
     للمعارف
    0.54
     
    0.54
    Хьажоргаш
    0.53
     doInBackground
    0.53
    Act Density 0.000%

    No Known Activations