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

    Neuronpedia

    INDEX
    Explanations

    asking about states and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grandmother
    0.43
     grandfather
    0.43
    ankle
    0.43
    院校
    0.42
     notre
    0.40
     nostro
    0.40
     miglia
    0.39
     pediatric
    0.38
     nossas
    0.38
    ложи
    0.37
    POSITIVE LOGITS
     نفسك
    0.44
     Likewise
    0.44
     li
    0.43
     lich
    0.41
     ሁኔታ
    0.41
     souvenirs
    0.41
     exhibitions
    0.40
     Evolution
    0.40
     Actions
    0.39
     Diplomacy
    0.39
    Act Density 0.001%

    No Known Activations