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

    Neuronpedia

    INDEX
    Explanations

    economic moat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     زنج
    0.42
    DID
    0.37
    抗菌
    0.36
    pH
    0.36
    skcipher
    0.36
    尃
    0.36
    Esto
    0.35
    ANGMAR
    0.35
    fähig
    0.35
     LIVING
    0.34
    POSITIVE LOGITS
     pulls
    0.42
    rije
    0.41
    iss
    0.41
    des
    0.40
    itelisted
    0.39
    stil
    0.39
    usele
    0.38
    nesi
    0.38
     suggests
    0.38
     represents
    0.37
    Act Density 0.001%

    No Known Activations