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

    Neuronpedia

    INDEX
    Explanations

    actions related to marking or classifying items

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

    mark as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    weg
    -0.37
    SpringBootTest
    -0.36
     للاسماء
    -0.35
     chaussure
    -0.34
     useContext
    -0.34
    wechsel
    -0.33
     uſe
    -0.33
    sbericht
    -0.33
     match
    -0.32
     cab
    -0.31
    POSITIVE LOGITS
     marking
    0.79
     marked
    0.77
    marked
    0.77
     Marking
    0.76
    Marked
    0.75
    Marking
    0.74
    marking
    0.71
     Мексичка
    0.71
    MLLoader
    0.71
     Biôgrafia
    0.70
    Act Density 0.045%

    No Known Activations