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

    Neuronpedia

    INDEX
    Explanations

    historic centre

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lloyd
    0.49
     Shanghai
    0.47
    Shanghai
    0.46
     …
    0.44
    ...+
    0.44
    h
    0.44
     Coney
    0.43
    🧅
    0.43
    BANG
    0.42
     Lloyd
    0.42
    POSITIVE LOGITS
     końcu
    0.50
    υν
    0.47
    nętr
    0.47
     попа
    0.47
    荅
    0.46
     ပါ
    0.46
     rechte
    0.44
    सूचित
    0.44
    েনারেল
    0.44
     trả
    0.43
    Act Density 0.001%

    No Known Activations