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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidance and providing instructions for actions or decisions

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

    instructions and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verder
    -0.32
     judiciales
    -0.32
    haja
    -0.31
    ancers
    -0.30
     ffilm
    -0.30
     ofrecerte
    -0.30
    สถ
    -0.30
    際
    -0.30
    InteropServices
    -0.30
     mau
    -0.29
    POSITIVE LOGITS
    saraba
    0.65
    AutoField
    0.56
     تكبرها
    0.56
     cherchés
    0.56
    __":
    0.55
     kasarigan
    0.55
    tvguidetime
    0.54
    期刊论文
    0.52
    webElementGuid
    0.51
     utafitiHapana
    0.50
    Act Density 0.284%

    No Known Activations