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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific types of products or items, particularly those that are commonly used or referenced in various contexts

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

    technical terms and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteBarrier
    -0.47
     Moyen
    -0.41
     voisin
    -0.40
     pinulongan
    -0.37
     flamen
    -0.37
    Obrázky
    -0.36
     Longitud
    -0.36
    Tikang
    -0.36
    คัญ
    -0.36
     Krzysz
    -0.36
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.49
    AISSEE
    0.46
    setVerticalGroup
    0.44
    WriteTagHelper
    0.42
    Ӕ
    0.42
    GenerationType
    0.41
     OMITBAD
    0.41
     Trapp
    0.40
     <>",
    0.40
    mobileqq
    0.40
    Act Density 0.052%

    No Known Activations