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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to data types and class definitions in code

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

    starts with user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мәкал
    -0.92
     Infórmanos
    -0.80
    évaluateur
    -0.75
    تقاوى
    -0.73
    webElementGuid
    -0.71
     Chwiliwch
    -0.71
     وتسجيلات
    -0.70
    ReusableCell
    -0.69
    IVEREF
    -0.68
    tagHelperRunner
    -0.68
    POSITIVE LOGITS
    ArgsConstructor
    0.29
    AntiForgeryToken
    0.28
    <eos>
    0.28
     Kammer
    0.28
     sarili
    0.27
     MonoBehaviour
    0.27
    卷
    0.26
    Step
    0.26
     skr
    0.26
    InstanceState
    0.25
    Act Density 0.003%

    No Known Activations