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

    Neuronpedia

    INDEX
    Explanations

    elements related to technical specifications or methodologies in documents

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

    code, math, or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.59
     تضيفلها
    -0.52
     الحره
    -0.52
    Identyfik
    -0.48
    WriteTagHelper
    -0.48
     referrerpolicy
    -0.45
    сылкі
    -0.44
    EDEFAULT
    -0.44
    WriteBarrier
    -0.43
    Referencie
    -0.43
    POSITIVE LOGITS
    disposing
    0.43
    AlterField
    0.40
     Infórmanos
    0.38
    ∉
    0.37
     core
    0.37
     הת
    0.36
    JsonHelper
    0.36
    FLAT
    0.36
     Outside
    0.35
    <caption>
    0.35
    Act Density 0.257%

    No Known Activations