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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating restrictions or limitations

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

    technical programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kew
    -0.42
    InjectMocks
    -0.40
     تضيفلها
    -0.39
     лу
    -0.39
     stuff
    -0.38
    ToDecimal
    -0.38
    })()
    -0.37
    Sim
    -0.37
     retro
    -0.37
     Wich
    -0.37
    POSITIVE LOGITS
     gethan
    0.64
     protoimpl
    0.62
     Италијани
    0.47
    تفصیلات
    0.47
    AddTagHelper
    0.47
    desertcart
    0.47
    EDEFAULT
    0.46
    PreferredItem
    0.46
    elemField
    0.45
    resizingMask
    0.45
    Act Density 0.000%

    No Known Activations